docs: 전략 post-mortem — 7전 7패 분석 및 다음 방향 제안

- 공통 실패 패턴 3가지 (IS/OOS 격차, 대칭성 실패, 필터 역효과) - 근본 원인: 공개 시그널 방향 예측 패러다임 한계 - 다음 방향: 패러다임 변경(stat arb), 비용 절감(maker), 데이터 확장 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
research: MTF + BTC 추세 필터 백테스트 — FAIL, MTF 전략 최종 폐기
2026-05-04 09:30:10 +09:00 · 2026-05-04 09:24:45 +09:00 · 2026-05-04 09:03:06 +09:00 · 2026-05-04 09:03:03 +09:00 · 2026-05-04 09:03:02 +09:00 · 2026-05-04 09:02:57 +09:00
75 changed files with 131997 additions and 28 deletions
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -65,7 +65,7 @@ bash scripts/deploy_model.sh --symbol XRPUSDT
 4. `src/exchange.py` + `src/risk_manager.py` — Dynamic margin, MARKET orders with SL/TP, daily loss limit (5%), same-direction limit
 5. `src/user_data_stream.py` + `src/notifier.py` — Real-time TP/SL detection via WebSocket, Discord webhooks

-**Dual-layer kill switch** (per-symbol, in `src/bot.py`): Fast Kill (8 consecutive net losses) + Slow Kill (last 15 trades PF < 0.75). Trade history persisted to `data/trade_history/{symbol}.jsonl`. Blocks new entries only; existing SL/TP exits work normally. Manual reset via `RESET_KILL_SWITCH_{SYMBOL}=True` env var + restart.
+**Dual-layer kill switch** (per-symbol, in `src/bot.py` and `src/mtf_bot.py`): Fast Kill (8 consecutive net losses) + Slow Kill (last 15 trades PF < 0.75). Trade history persisted to `data/trade_history/{symbol}.jsonl`. Blocks new entries only; existing SL/TP exits work normally. Manual reset via `RESET_KILL_SWITCH_{SYMBOL}=True` (main bot) or `RESET_KILL_SWITCH_MTF_{SYMBOL}=True` (MTF bot) env var + restart. MTF bot uses bps-based PnL for kill switch decisions.

 **Parallel execution**: Per-symbol bots run independently via `asyncio.gather()`. Each bot's `user_data_stream` also runs in parallel.

@@ -154,4 +154,8 @@ All design documents and implementation plans are stored in `docs/plans/` with t
 | 2026-03-30 | `ls-ratio-backtest` (design + result) | Edge 없음 확정, 폐기 |
 | 2026-03-30 | `fr-oi-backtest` (result) | SHORT PF=1.88이나 대칭성 실패(Case2), 폐기 |
 | 2026-03-30 | `public-api-research-closed` | Binance 공개 API 전수 테스트 완료, 단독 edge 없음 |
-| 2026-03-30 | `mtf-pullback-bot` | MTF Pullback Bot 배포, 4월 OOS Dry-run 검증 진행 중 |
+| 2026-03-30 | `mtf-pullback-bot` | MTF Pullback Bot — **최종 폐기** (OOS+BTC필터 모두 실패) |
+| 2026-04-21 | `mtf-oos-dryrun-result` | 중간 보고 — 24건 Raw PF 0.98 |
+| 2026-05-04 | `mtf-oos-final-result` | **FAIL, 폐기** — 30건 fees_only PF 0.84, SHORT 대칭성 실패 |
+| 2026-05-04 | `mtf-btc-filter` (design + result) | **FAIL, 최종 폐기** — BTC 필터 추가해도 OOS PF 0.90, 베이스라인보다 악화 |
+| 2026-05-04 | `strategy-post-mortem` | 7전 7패 분석 — 공개 시그널 방향 예측 패러다임 한계, 다음 방향 제안 |
--- a/data/btcusdt/ls_ratio_15m.parquet
+++ b/data/btcusdt/ls_ratio_15m.parquet
--- a/data/dogeusdt/combined_15m.parquet
+++ b/data/dogeusdt/combined_15m.parquet
--- a/data/ethusdt/ls_ratio_15m.parquet
+++ b/data/ethusdt/ls_ratio_15m.parquet
--- a/data/trade_history/mtf_testusdt.jsonl
+++ b/data/trade_history/mtf_testusdt.jsonl
@@ -0,0 +1,8 @@
+{"symbol": "TESTUSDT", "side": "SHORT", "entry_price": 2.0, "entry_ts": "2026-04-03T08:48:46.103465+00:00", "exit_price": 2.015, "exit_ts": "2026-04-03T08:48:46.103523+00:00", "sl_price": 2.015, "tp_price": 1.977, "atr": 0.01, "pnl_bps": -75.0, "reason": "SL \ud788\ud2b8"}
+{"symbol": "TESTUSDT", "side": "SHORT", "entry_price": 2.0, "entry_ts": "2026-04-03T08:48:46.103862+00:00", "exit_price": 2.015, "exit_ts": "2026-04-03T08:48:46.103922+00:00", "sl_price": 2.015, "tp_price": 1.977, "atr": 0.01, "pnl_bps": -75.0, "reason": "SL \ud788\ud2b8"}
+{"symbol": "TESTUSDT", "side": "SHORT", "entry_price": 2.0, "entry_ts": "2026-04-03T08:49:26.310084+00:00", "exit_price": 2.015, "exit_ts": "2026-04-03T08:49:26.310144+00:00", "sl_price": 2.015, "tp_price": 1.977, "atr": 0.01, "pnl_bps": -75.0, "reason": "SL \ud788\ud2b8"}
+{"symbol": "TESTUSDT", "side": "SHORT", "entry_price": 2.0, "entry_ts": "2026-04-03T08:49:26.310514+00:00", "exit_price": 2.015, "exit_ts": "2026-04-03T08:49:26.310577+00:00", "sl_price": 2.015, "tp_price": 1.977, "atr": 0.01, "pnl_bps": -75.0, "reason": "SL \ud788\ud2b8"}
+{"symbol": "TESTUSDT", "side": "SHORT", "entry_price": 2.0, "entry_ts": "2026-04-17T01:57:57.242077+00:00", "exit_price": 2.015, "exit_ts": "2026-04-17T01:57:57.242137+00:00", "sl_price": 2.015, "tp_price": 1.977, "atr": 0.01, "pnl_bps": -75.0, "reason": "SL \ud788\ud2b8"}
+{"symbol": "TESTUSDT", "side": "SHORT", "entry_price": 2.0, "entry_ts": "2026-04-17T01:57:57.242824+00:00", "exit_price": 2.015, "exit_ts": "2026-04-17T01:57:57.242904+00:00", "sl_price": 2.015, "tp_price": 1.977, "atr": 0.01, "pnl_bps": -75.0, "reason": "SL \ud788\ud2b8"}
+{"symbol": "TESTUSDT", "side": "SHORT", "entry_price": 2.0, "entry_ts": "2026-04-17T01:59:56.588979+00:00", "exit_price": 2.015, "exit_ts": "2026-04-17T01:59:56.589032+00:00", "sl_price": 2.015, "tp_price": 1.977, "atr": 0.01, "pnl_bps": -75.0, "reason": "SL \ud788\ud2b8"}
+{"symbol": "TESTUSDT", "side": "SHORT", "entry_price": 2.0, "entry_ts": "2026-04-17T01:59:56.589321+00:00", "exit_price": 2.015, "exit_ts": "2026-04-17T01:59:56.589381+00:00", "sl_price": 2.015, "tp_price": 1.977, "atr": 0.01, "pnl_bps": -75.0, "reason": "SL \ud788\ud2b8"}
--- a/data/trade_history/mtf_xrpusdt.jsonl
+++ b/data/trade_history/mtf_xrpusdt.jsonl
@@ -0,0 +1,6 @@
+{"symbol": "XRPUSDT", "side": "LONG", "entry_price": 2.0, "entry_ts": "2026-03-31T02:09:25.326276+00:00", "exit_price": 2.01, "exit_ts": "2026-03-31T02:09:25.326333+00:00", "sl_price": 1.985, "tp_price": 2.023, "atr": 0.01, "pnl_bps": 50, "reason": "test"}
+{"symbol": "XRPUSDT", "side": "LONG", "entry_price": 2.0, "entry_ts": "2026-03-31T02:10:01.522854+00:00", "exit_price": 2.01, "exit_ts": "2026-03-31T02:10:01.522915+00:00", "sl_price": 1.985, "tp_price": 2.023, "atr": 0.01, "pnl_bps": 50, "reason": "test"}
+{"symbol": "XRPUSDT", "side": "LONG", "entry_price": 2.0, "entry_ts": "2026-04-03T08:48:46.101315+00:00", "exit_price": 2.01, "exit_ts": "2026-04-03T08:48:46.101362+00:00", "sl_price": 1.985, "tp_price": 2.023, "atr": 0.01, "pnl_bps": 50, "reason": "test"}
+{"symbol": "XRPUSDT", "side": "LONG", "entry_price": 2.0, "entry_ts": "2026-04-03T08:49:26.307772+00:00", "exit_price": 2.01, "exit_ts": "2026-04-03T08:49:26.307825+00:00", "sl_price": 1.985, "tp_price": 2.023, "atr": 0.01, "pnl_bps": 50, "reason": "test"}
+{"symbol": "XRPUSDT", "side": "LONG", "entry_price": 2.0, "entry_ts": "2026-04-17T01:57:57.239531+00:00", "exit_price": 2.01, "exit_ts": "2026-04-17T01:57:57.239584+00:00", "sl_price": 1.985, "tp_price": 2.023, "atr": 0.01, "pnl_bps": 50, "reason": "test"}
+{"symbol": "XRPUSDT", "side": "LONG", "entry_price": 2.0, "entry_ts": "2026-04-17T01:59:56.586709+00:00", "exit_price": 2.01, "exit_ts": "2026-04-17T01:59:56.586758+00:00", "sl_price": 1.985, "tp_price": 2.023, "atr": 0.01, "pnl_bps": 50, "reason": "test"}
--- a/data/trade_history/mtf_xrpusdtusdt.jsonl
+++ b/data/trade_history/mtf_xrpusdtusdt.jsonl
@@ -0,0 +1,30 @@
+{"symbol": "XRP/USDT:USDT", "side": "SHORT", "entry_price": 1.2924, "entry_ts": "2026-04-02T15:45:02.285284+00:00", "exit_price": 1.3011924698057984, "exit_ts": "2026-04-02T17:00:00.791551+00:00", "sl_price": 1.3011924698057984, "tp_price": 1.2789182129644425, "atr": 0.005861646537198913, "pnl_bps": -68.0, "reason": "SL \ud788\ud2b8 (1.3012)"}
+{"symbol": "XRP/USDT:USDT", "side": "SHORT", "entry_price": 1.299, "entry_ts": "2026-04-02T18:15:02.275070+00:00", "exit_price": 1.3076847690550104, "exit_ts": "2026-04-02T20:30:00.977600+00:00", "sl_price": 1.3076847690550104, "tp_price": 1.2856833541156505, "atr": 0.005789846036673716, "pnl_bps": -66.9, "reason": "SL \ud788\ud2b8 (1.3077)"}
+{"symbol": "XRP/USDT:USDT", "side": "SHORT", "entry_price": 1.3372, "entry_ts": "2026-04-06T07:30:02.964551+00:00", "exit_price": 1.343892780041389, "exit_ts": "2026-04-06T08:15:00.323145+00:00", "sl_price": 1.343892780041389, "tp_price": 1.3269377372698703, "atr": 0.004461853360925946, "pnl_bps": -50.1, "reason": "SL \ud788\ud2b8 (1.3439)"}
+{"symbol": "XRP/USDT:USDT", "side": "SHORT", "entry_price": 1.338, "entry_ts": "2026-04-06T09:15:02.357616+00:00", "exit_price": 1.34426520318828, "exit_ts": "2026-04-06T09:30:00.575381+00:00", "sl_price": 1.34426520318828, "tp_price": 1.328393355111304, "atr": 0.004176802125519994, "pnl_bps": -46.8, "reason": "SL \ud788\ud2b8 (1.3443)"}
+{"symbol": "XRP/USDT:USDT", "side": "SHORT", "entry_price": 1.3489, "entry_ts": "2026-04-06T11:45:02.281455+00:00", "exit_price": 1.337093964326515, "exit_ts": "2026-04-06T17:30:00.471399+00:00", "sl_price": 1.3565995884827076, "tp_price": 1.337093964326515, "atr": 0.005133058988471726, "pnl_bps": 87.5, "reason": "TP \ud788\ud2b8 (1.3371)"}
+{"symbol": "XRP/USDT:USDT", "side": "SHORT", "entry_price": 1.3169, "entry_ts": "2026-04-07T05:15:02.864543+00:00", "exit_price": 1.3067678775397529, "exit_ts": "2026-04-07T11:15:00.824550+00:00", "sl_price": 1.323507905952335, "tp_price": 1.3067678775397529, "atr": 0.004405270634889999, "pnl_bps": 76.9, "reason": "TP \ud788\ud2b8 (1.3068)"}
+{"symbol": "XRP/USDT:USDT", "side": "SHORT", "entry_price": 1.3025, "entry_ts": "2026-04-07T19:00:02.557934+00:00", "exit_price": 1.309204644912873, "exit_ts": "2026-04-07T20:15:00.598047+00:00", "sl_price": 1.309204644912873, "tp_price": 1.292219544466928, "atr": 0.004469763275248652, "pnl_bps": -51.5, "reason": "SL \ud788\ud2b8 (1.3092)"}
+{"symbol": "XRP/USDT:USDT", "side": "LONG", "entry_price": 1.3794, "entry_ts": "2026-04-08T08:15:03.067336+00:00", "exit_price": 1.3681020223721523, "exit_ts": "2026-04-08T14:45:00.843687+00:00", "sl_price": 1.3681020223721523, "tp_price": 1.3967235656960328, "atr": 0.007531985085231735, "pnl_bps": -81.9, "reason": "SL \ud788\ud2b8 (1.3681)"}
+{"symbol": "XRP/USDT:USDT", "side": "LONG", "entry_price": 1.3525, "entry_ts": "2026-04-08T22:15:02.356148+00:00", "exit_price": 1.342647301335702, "exit_ts": "2026-04-08T23:15:00.470216+00:00", "sl_price": 1.342647301335702, "tp_price": 1.3676074712852568, "atr": 0.006568465776198652, "pnl_bps": -72.8, "reason": "SL \ud788\ud2b8 (1.3426)"}
+{"symbol": "XRP/USDT:USDT", "side": "LONG", "entry_price": 1.3324, "entry_ts": "2026-04-09T05:30:02.831310+00:00", "exit_price": 1.3242694197294704, "exit_ts": "2026-04-09T14:45:00.646118+00:00", "sl_price": 1.3242694197294704, "tp_price": 1.3448668897481453, "atr": 0.005420386847019691, "pnl_bps": -61.0, "reason": "SL \ud788\ud2b8 (1.3243)"}
+{"symbol": "XRP/USDT:USDT", "side": "LONG", "entry_price": 1.33, "entry_ts": "2026-04-12T09:45:02.575343+00:00", "exit_price": 1.3234444290752214, "exit_ts": "2026-04-12T14:15:00.701105+00:00", "sl_price": 1.3234444290752214, "tp_price": 1.3400518754179942, "atr": 0.0043703806165191405, "pnl_bps": -49.3, "reason": "SL \ud788\ud2b8 (1.3234)"}
+{"symbol": "XRP/USDT:USDT", "side": "LONG", "entry_price": 1.3314, "entry_ts": "2026-04-12T20:45:04.130138+00:00", "exit_price": 1.3260943015416145, "exit_ts": "2026-04-12T22:45:00.641365+00:00", "sl_price": 1.3260943015416145, "tp_price": 1.3395354043028576, "atr": 0.0035371323055903036, "pnl_bps": -39.9, "reason": "SL \ud788\ud2b8 (1.3261)"}
+{"symbol": "XRP/USDT:USDT", "side": "LONG", "entry_price": 1.3662, "entry_ts": "2026-04-14T02:00:03.591231+00:00", "exit_price": 1.3826215436611005, "exit_ts": "2026-04-14T14:00:00.219774+00:00", "sl_price": 1.355490297612326, "tp_price": 1.3826215436611005, "atr": 0.007139801591782776, "pnl_bps": 120.2, "reason": "TP \ud788\ud2b8 (1.3826)"}
+{"symbol": "XRP/USDT:USDT", "side": "LONG", "entry_price": 1.3773, "entry_ts": "2026-04-14T16:30:03.036264+00:00", "exit_price": 1.36621231930106, "exit_ts": "2026-04-14T18:30:00.959397+00:00", "sl_price": 1.36621231930106, "tp_price": 1.3943011104050413, "atr": 0.007391787132626665, "pnl_bps": -80.5, "reason": "SL \ud788\ud2b8 (1.3662)"}
+{"symbol": "XRP/USDT:USDT", "side": "LONG", "entry_price": 1.3917, "entry_ts": "2026-04-16T00:15:02.437176+00:00", "exit_price": 1.404348303100205, "exit_ts": "2026-04-16T03:00:00.439541+00:00", "sl_price": 1.3834511066737791, "tp_price": 1.404348303100205, "atr": 0.00549926221748051, "pnl_bps": 90.9, "reason": "TP \ud788\ud2b8 (1.4043)"}
+{"symbol": "XRP/USDT:USDT", "side": "LONG", "entry_price": 1.4039, "entry_ts": "2026-04-16T05:45:02.587650+00:00", "exit_price": 1.4150432459353304, "exit_ts": "2026-04-16T09:30:00.120795+00:00", "sl_price": 1.3966326656943495, "tp_price": 1.4150432459353304, "atr": 0.004844889537100242, "pnl_bps": 79.4, "reason": "TP \ud788\ud2b8 (1.4150)"}
+{"symbol": "XRP/USDT:USDT", "side": "LONG", "entry_price": 1.4089, "entry_ts": "2026-04-16T12:15:03.065202+00:00", "exit_price": 1.4209071868858967, "exit_ts": "2026-04-16T13:45:00.389284+00:00", "sl_price": 1.4010692259439805, "tp_price": 1.4209071868858967, "atr": 0.005220516037346328, "pnl_bps": 85.2, "reason": "TP \ud788\ud2b8 (1.4209)"}
+{"symbol": "XRP/USDT:USDT", "side": "LONG", "entry_price": 1.4199, "entry_ts": "2026-04-16T17:45:03.104428+00:00", "exit_price": 1.4339129204091046, "exit_ts": "2026-04-16T19:00:00.181964+00:00", "sl_price": 1.4107611388636274, "tp_price": 1.4339129204091046, "atr": 0.006092574090915036, "pnl_bps": 98.7, "reason": "TP \ud788\ud2b8 (1.4339)"}
+{"symbol": "XRP/USDT:USDT", "side": "LONG", "entry_price": 1.4827, "entry_ts": "2026-04-17T19:30:03.006514+00:00", "exit_price": 1.4672241636153258, "exit_ts": "2026-04-18T04:30:00.884113+00:00", "sl_price": 1.4672241636153258, "tp_price": 1.5064296157898336, "atr": 0.010317224256449408, "pnl_bps": -104.4, "reason": "SL \ud788\ud2b8 (1.4672)"}
+{"symbol": "XRP/USDT:USDT", "side": "LONG", "entry_price": 1.4303, "entry_ts": "2026-04-18T21:30:02.340862+00:00", "exit_price": 1.422038986984328, "exit_ts": "2026-04-19T06:30:00.566171+00:00", "sl_price": 1.422038986984328, "tp_price": 1.4429668866240302, "atr": 0.005507342010447945, "pnl_bps": -57.8, "reason": "SL \ud788\ud2b8 (1.4220)"}
+{"symbol": "XRP/USDT:USDT", "side": "LONG", "entry_price": 1.4221, "entry_ts": "2026-04-19T11:00:02.406765+00:00", "exit_price": 1.4317857929446725, "exit_ts": "2026-04-19T13:30:00.147036+00:00", "sl_price": 1.415783178514344, "tp_price": 1.4317857929446725, "atr": 0.004211214323770682, "pnl_bps": 68.1, "reason": "TP \ud788\ud2b8 (1.4318)"}
+{"symbol": "XRP/USDT:USDT", "side": "LONG", "entry_price": 1.4044, "entry_ts": "2026-04-20T00:45:02.394423+00:00", "exit_price": 1.3967874471566615, "exit_ts": "2026-04-20T06:00:00.011187+00:00", "sl_price": 1.3967874471566615, "tp_price": 1.4160725810264527, "atr": 0.005075035228892415, "pnl_bps": -54.2, "reason": "SL \ud788\ud2b8 (1.3968)"}
+{"symbol": "XRP/USDT:USDT", "side": "LONG", "entry_price": 1.4053, "entry_ts": "2026-04-20T06:45:03.160723+00:00", "exit_price": 1.4157391122980558, "exit_ts": "2026-04-20T07:45:00.033371+00:00", "sl_price": 1.3984918832838766, "tp_price": 1.4157391122980558, "atr": 0.00453874447741562, "pnl_bps": 74.3, "reason": "TP \ud788\ud2b8 (1.4157)"}
+{"symbol": "XRP/USDT:USDT", "side": "LONG", "entry_price": 1.414, "entry_ts": "2026-04-20T09:30:02.604341+00:00", "exit_price": 1.4264633526792339, "exit_ts": "2026-04-20T14:45:00.009801+00:00", "sl_price": 1.405871726513543, "tp_price": 1.4264633526792339, "atr": 0.005418848990971227, "pnl_bps": 88.1, "reason": "TP \ud788\ud2b8 (1.4265)"}
+{"symbol": "XRP/USDT:USDT", "side": "LONG", "entry_price": 1.4143, "entry_ts": "2026-04-23T12:00:03.002778+00:00", "exit_price": 1.4234400599181054, "exit_ts": "2026-04-23T15:00:00.077208+00:00", "sl_price": 1.4083390913577571, "tp_price": 1.4234400599181054, "atr": 0.003973939094828441, "pnl_bps": 64.6, "reason": "TP \ud788\ud2b8 (1.4234)"}
+{"symbol": "XRP/USDT:USDT", "side": "SHORT", "entry_price": 1.3924, "entry_ts": "2026-04-27T21:00:03.044720+00:00", "exit_price": 1.398856832668528, "exit_ts": "2026-04-28T00:00:00.585275+00:00", "sl_price": 1.398856832668528, "tp_price": 1.3824995232415904, "atr": 0.004304555112352007, "pnl_bps": -46.4, "reason": "SL \ud788\ud2b8 (1.3989)"}
+{"symbol": "XRP/USDT:USDT", "side": "SHORT", "entry_price": 1.3955, "entry_ts": "2026-04-28T02:45:02.809371+00:00", "exit_price": 1.3859950974494593, "exit_ts": "2026-04-28T11:30:00.636915+00:00", "sl_price": 1.4016988494894829, "tp_price": 1.3859950974494593, "atr": 0.004132566326322003, "pnl_bps": 68.1, "reason": "TP \ud788\ud2b8 (1.3860)"}
+{"symbol": "XRP/USDT:USDT", "side": "SHORT", "entry_price": 1.3791, "entry_ts": "2026-04-28T21:45:02.720338+00:00", "exit_price": 1.384214600169389, "exit_ts": "2026-04-29T03:45:00.543758+00:00", "sl_price": 1.384214600169389, "tp_price": 1.3712576130736036, "atr": 0.003409733446259308, "pnl_bps": -37.1, "reason": "SL \ud788\ud2b8 (1.3842)"}
+{"symbol": "XRP/USDT:USDT", "side": "SHORT", "entry_price": 1.3906, "entry_ts": "2026-04-29T09:00:02.842299+00:00", "exit_price": 1.39511977056087, "exit_ts": "2026-04-29T09:45:00.260020+00:00", "sl_price": 1.39511977056087, "tp_price": 1.3836696851399997, "atr": 0.0030131803739132297, "pnl_bps": -32.5, "reason": "SL \ud788\ud2b8 (1.3951)"}
+{"symbol": "XRP/USDT:USDT", "side": "SHORT", "entry_price": 1.395, "entry_ts": "2026-04-29T11:30:02.795097+00:00", "exit_price": 1.3865272285022556, "exit_ts": "2026-04-29T12:30:00.623489+00:00", "sl_price": 1.4005257205420072, "tp_price": 1.3865272285022556, "atr": 0.003683813694671445, "pnl_bps": 60.7, "reason": "TP \ud788\ud2b8 (1.3865)"}
--- a/data/trade_history/testnet/xrpusdt.jsonl
+++ b/data/trade_history/testnet/xrpusdt.jsonl
@@ -0,0 +1,15 @@
+{"net_pnl": -24.8291, "reason": "MANUAL", "ts": "2026-03-22T15:15:35.180527+00:00"}
+{"net_pnl": -34.2859, "reason": "MANUAL", "ts": "2026-03-22T15:20:06.214857+00:00"}
+{"net_pnl": -158.9121, "reason": "MANUAL", "ts": "2026-03-22T16:00:48.207128+00:00"}
+{"net_pnl": -350.7024, "reason": "MANUAL", "ts": "2026-03-23T03:53:54.960798+00:00"}
+{"net_pnl": 9.89, "reason": "MANUAL", "ts": "2026-03-23T03:59:32.078260+00:00"}
+{"net_pnl": -58.2073, "reason": "SL", "ts": "2026-03-23T04:01:58.094580+00:00"}
+{"net_pnl": -20.956, "reason": "SL", "ts": "2026-03-23T04:08:30.143579+00:00"}
+{"net_pnl": -12.4839, "reason": "SL", "ts": "2026-03-23T04:11:19.108516+00:00"}
+{"net_pnl": -28.8319, "reason": "SL", "ts": "2026-03-23T04:15:50.164001+00:00"}
+{"net_pnl": 120.289, "reason": "SL", "ts": "2026-03-23T04:42:02.062102+00:00"}
+{"net_pnl": -20.8975, "reason": "TP", "ts": "2026-03-23T05:31:24.070622+00:00"}
+{"net_pnl": -31.664, "reason": "MANUAL", "ts": "2026-03-23T06:01:18.223227+00:00"}
+{"net_pnl": 31.2816, "reason": "MANUAL", "ts": "2026-03-23T06:30:11.651964+00:00"}
+{"net_pnl": -78.5471, "reason": "MANUAL", "ts": "2026-03-23T07:05:18.387993+00:00"}
+{"net_pnl": -1.2852, "reason": "SL", "ts": "2026-03-23T07:08:40.080152+00:00"}
--- a/data/trxusdt/combined_15m.parquet
+++ b/data/trxusdt/combined_15m.parquet
--- a/data/xrpusdt/combined_15m.parquet
+++ b/data/xrpusdt/combined_15m.parquet
--- a/data/xrpusdt/combined_15m.parquet.bak
+++ b/data/xrpusdt/combined_15m.parquet.bak
--- a/data/xrpusdt/ls_ratio_15m.parquet
+++ b/data/xrpusdt/ls_ratio_15m.parquet
--- a/docs/plans/2026-03-30-fr-oi-backtest-result.md
+++ b/docs/plans/2026-03-30-fr-oi-backtest-result.md
@@ -0,0 +1,52 @@
+# FR × OI 변화율 백테스트 결과: 폐기
+
+**Date**: 2026-03-30
+**Status**: REJECTED — 대칭성 실패 (Case 2), 시장 베타 의심
+**Decision**: 설계 기준 준수, 폐기
+
+## 상관분석 결과
+
+| 피처 | → 4h | N |
+|------|------|---|
+| FR × OI변화율(1h) | r = -0.1734 | 448 |
+| FR × OI변화율 | r = -0.0944 | 451 |
+| OI 변화율 (1h) | r = +0.0916 | 448 |
+
+## 백테스트 결과 (12개 조합)
+
+| 조합 | 거래수 | PF | PnL(bps) |
+|------|--------|-----|----------|
+| SHORT 1h P75 | 36 | **1.88** | +304 |
+| SHORT 1h P50 | 63 | 1.07 | +54 |
+| SHORT 1h P25 | 80 | 1.16 | +163 |
+| SHORT 4h P75 | 17 | 1.68 | +314 |
+| SHORT 4h P50 | 23 | 1.56 | +327 |
+| SHORT 4h P25 | 26 | 1.50 | +303 |
+| LONG 전 조합 | — | **0.34~0.50** | 전부 손실 |
+
+## 폐기 근거 (3단계 필터)
+
+1. **필터 1 통과**: SHORT 1h P75 PF=1.88 > 1.5 ✓
+2. **필터 2 경고**: 36건 (🟡 참고만, 50건 미달) ⚠️
+3. **필터 3 실패**: LONG 전 조합 PF < 0.5 = Case 2 (한쪽만 성공) ✗
+
+**Case 2 = 시장 베타/우연. 폐기.**
+
+## 왜 SHORT만 작동했나
+
+- 데이터 기간: 3/1~3/30 (29일)
+- 이 기간 XRP: 하락 추세
+- SHORT가 잘 먹힌 건 시장 방향과 일치 (beta)
+- 상승장에서는 LONG이 작동하고 SHORT가 실패할 것
+
+## 4월 재검증 (선택사항)
+
+- 4/15: OI 29일 데이터로 동일 테스트 재실행
+- 상승장 구간 포함 시 SHORT PF 유지되는지 확인
+- 여전히 Case 2면 확정 폐기
+
+## 교훈
+
+- PF 1.88을 거절한 이유: 대칭성 없는 시그널은 시장 방향에 의존
+- "한 방향만 작동"은 가장 흔한 과적합 패턴
+- 설계 기준을 사전에 세우고 준수하는 것이 생존 전략
--- a/docs/plans/2026-03-30-ls-ratio-backtest-design.md
+++ b/docs/plans/2026-03-30-ls-ratio-backtest-design.md
@@ -0,0 +1,76 @@
+# L/S Ratio 단독 백테스트 설계
+
+**Date**: 2026-03-30
+**Status**: Approved
+**Goal**: L/S ratio의 독립적 edge 유무를 빠르게 판정
+
+## 배경
+
+- 기존 시그널(RSI+MACD+BB+EMA+StochRSI)은 PF 0.89, 수익성 부족 확정 (2026-03-29)
+- L/S ratio 수집 중 (3/22~, 프로덕션 716행)
+- 이전 분석에서 XRP top_acct_ls_ratio → 1h return 상관계수 +0.1158 (Momentum)
+
+## Phase 1: Pure Edge Test
+
+### 데이터
+- L/S ratio: 프로덕션 수집 (716행, 3/22~3/30)
+- Kline: Binance XRPUSDT 15m (같은 기간)
+- 비교용: BTC/ETH L/S ratio
+
+### 전략 로직
+- 진입: `top_acct_ls_ratio` 백분위수 기반 임계값
+- 보유: 고정 4캔들 (1시간)
+- 청산: 1시간 후 종가
+- 수수료: 0.04% × 2 = 0.08%
+- 포지션: 1건씩만
+
+### 테스트 조합 (6개)
+
+| 임계값 | 방향 | 신호 |
+|--------|------|------|
+| 75th %ile | LONG | 모멘텀 강함 |
+| 75th %ile | SHORT | 모멘텀 약함 |
+| 50th %ile | LONG | 모멘텀 중간 |
+| 50th %ile | SHORT | 모멘텀 중간 |
+| 25th %ile | LONG | 모멘텀 약함 |
+| 25th %ile | SHORT | 모멘텀 강함 |
+
+### PF 계산
+- PF = Σ(Gross Profit - 비용) / Σ(|Gross Loss| + 비용)
+- 비용: 0.08% per trade
+
+### 판정 기준 (3단계 필터)
+
+**필터 1: 명확한 신호**
+- PF > 1.5 → edge 있음
+- PF < 0.5 → 실패
+- 0.5~1.5 → 판단 보류
+
+**필터 2: 거래수 신뢰도**
+- < 20건 → 🔴 폐기
+- 20~50건 → 🟡 참고만
+- 50~100건 → 🟢 검토
+- 100건+ → 🟢 우선
+
+**필터 3: 대칭성**
+- Case 1: LONG > 1.5 AND SHORT > 1.5 → 진정한 edge → Phase 2 진행
+- Case 2: 한쪽만 성공 → 시장 베타/우연 → 폐기
+- Case 3: 한쪽 강함 + 한쪽 애매 → 부분적 edge → 낮은 신뢰도로 Phase 2
+
+## Phase 2: Bot Simulation (조건부)
+
+Phase 1 필터 통과 시에만:
+- L/S ratio로 RSI/MACD 완전 대체
+- ATR SL 1.5x, TP 2.3x (기존 동일)
+- 역신호 시 반대 포지션 재진입
+
+## Phase 3: 4월 15일 재검증
+
+- 4/1~4/15 데이터로 동일 로직 재실행
+- 기준: PF > 1.15
+- GO/STOP/HOLD 최종 판정
+
+## 한계
+- 8일 = ~700 시그널 포인트, 조합당 ~115개
+- 극심한 과적합 위험 → 8일 결과는 "방향성 힌트"
+- 최종 판정은 4월 15일 재검증 기반
--- a/docs/plans/2026-03-30-ls-ratio-backtest-result.md
+++ b/docs/plans/2026-03-30-ls-ratio-backtest-result.md
@@ -0,0 +1,43 @@
+# L/S Ratio 백테스트 결과: Edge 없음
+
+**Date**: 2026-03-30
+**Status**: CLOSED — Edge 없음 확정, 폐기
+**Decision**: Option B (결과 수용 + 방향 전환)
+
+## 테스트 요약
+
+- 데이터: 8일 (3/22~3/30), 716 candles, XRPUSDT top_acct_ls_ratio
+- 방법: 6개 조합 (3 percentile × 2 direction), 1시간 보유, 수수료 0.08%
+- 판정 기준: PF > 1.5 + 거래수 > 20 + 양방향 대칭
+
+## 결과
+
+| 조합 | 거래수 | 승률 | PF | PnL(bps) |
+|------|--------|------|----|----------|
+| P75 LONG (모멘텀) | 39 | 35.9% | 0.53 | -306 |
+| P75 SHORT (역모멘텀) | 39 | 46.2% | 0.51 | -314 |
+| P50 LONG | 76 | 34.2% | 0.38 | -1252 |
+| P50 SHORT | 75 | 44.0% | 0.63 | -699 |
+| P25 LONG (역모멘텀) | 41 | 41.5% | 0.86 | -161 |
+| P25 SHORT (모멘텀) | 41 | 48.8% | 0.64 | -466 |
+
+**6개 조합 전부 PF < 1.0. 최고값 0.86은 기존 시그널(0.89)보다 못함.**
+
+## 판정 근거
+
+1. 상관분석 r=0.1158 (약함) → 거래비용 커버 불가 예상 → 백테스트로 확인
+2. Momentum도 Contrarian도 작동 안 함
+3. 추가 조합 테스트는 과적합 위험 (8일 데이터에 20+ 조합 = 우연의 승자 필연)
+
+## 다음 단계
+
+- L/S ratio 단독 시그널 폐기
+- collector는 유지 (4/15 재검증용 + 향후 복합 피처 가능성)
+- 새 데이터 소스 탐색: Funding Rate, OI Velocity, Close Ratio, USDT Perp Inflows
+- 4/15: L/S ratio 24일 재검증 (마지막 확인, 여전히 실패 시 확정 폐기)
+
+## 교훈
+
+- 약한 상관계수(r < 0.15)는 거래비용 후 수익 불가능 시사
+- "혹시 다른 형태로는?" = curve-fitting의 시작
+- 빠르게 실패하고 폐기하는 것이 생존 능력
--- a/docs/plans/2026-03-30-public-api-research-closed.md
+++ b/docs/plans/2026-03-30-public-api-research-closed.md
@@ -0,0 +1,40 @@
+# Binance Public API Signal Research: 공식 종료
+
+**Date**: 2026-03-30
+**Status**: CLOSED — 단독 edge 가진 피처 없음
+
+## 전수 테스트 결과
+
+| # | 피처 | 상관계수 | 백테스트 Best PF | 판정 |
+|---|------|---------|-----------------|------|
+| 1 | RSI+MACD+BB+EMA+StochRSI | — | 0.89 | 폐기 (수익성 부족) |
+| 2 | top_acct_ls_ratio | r=+0.116 (1h) | 0.86 | 폐기 (전 조합 < 1.0) |
+| 3 | global_ls_ratio | r=+0.048 (1h) | — | 약함, 미실시 |
+| 4 | top_pos_ls_ratio | r=+0.032 (1h) | — | 약함, 미실시 |
+| 5 | Funding Rate | r=-0.054 (4h) | — | 약함, 미실시 |
+| 6 | FR × OI변화율(1h) | r=-0.173 (4h) | SHORT 1.88 / LONG 0.50 | 폐기 (대칭성 실패) |
+| 7 | Taker Buy/Sell Ratio | r=-0.079 (1h) | 0.93 | 폐기 (전 조합 < 1.0) |
+| 8 | Liquidation (allForceOrders) | API 폐기됨 | — | 사용 불가 |
+
+## 핵심 교훈
+
+1. **r < 0.15는 거래비용(0.08%) 커버 불가** — 모든 피처에서 확인
+2. **대칭성(LONG+SHORT) 없는 시그널은 시장 베타** — FR×OI에서 확인
+3. **8일~29일 데이터는 "방향성 힌트"** — 최종 판정엔 더 긴 기간 필요
+4. **PF 1.88도 거절할 수 있어야 함** — 설계 기준 사전 수립이 핵심
+
+## 4월 15일 재검증
+
+- crontab 등록 완료 (프로덕션 10.1.10.24)
+- `scripts/revalidate_apr15.py` — L/S ratio + FR×OI 동시 재실행
+- 추가 데이터(24일/29일)로 동일 테스트
+- 여전히 실패 시 확정 폐기
+
+## 다음 방향 (4월 이후)
+
+Binance 공개 API 한정으로는 단독 edge 불가. 탐색 필요:
+- 온체인 데이터 (whale wallet tracking, exchange inflow/outflow)
+- 크로스 거래소 데이터 (OKX, Bybit OI/FR 차이)
+- 소셜 센티먼트 (Fear & Greed, Twitter/X sentiment)
+- 멀티피처 복합 시그널 (ML with L/S + FR + OI + Taker 조합)
+- 다른 타임프레임 (1h, 4h candle 기반)
--- a/docs/plans/2026-04-01-mtf_backtest.md
+++ b/docs/plans/2026-04-01-mtf_backtest.md
@@ -0,0 +1,30 @@
+【MTF 백테스트: 기존 vs 개선】
+
+데이터:
+├─ XRPUSDT kline (15m, 2026-02-01 ~ 현재)
+├─ 타겟: 다음 4시간 수익률
+└─ 기간: 2개월
+
+Step 1: 기존 신호 백테스트
+├─ 신호: 15분봉 RSI+MACD (메타필터 없음)
+├─ SL: ATR 1.5x, TP: ATR 2.3x
+├─ 결과 기대값: PF ≈ 0.89 (이미 알고 있는 값)
+└─ 거래수: X건
+
+Step 2: MTF 필터링 적용 백테스트
+├─ Meta Filter 1: 1h EMA 50 vs EMA 200
+├─ Meta Filter 2: 1h ADX > 20
+├─ Trigger: 15분봉 RSI+MACD (필터 조건과 일치할 때만)
+├─ SL: ATR 1.5x, TP: ATR 2.3x (동일)
+├─ 결과 기대값: PF > 1.0 (목표)
+└─ 거래수: Y건 (X의 40~60%)
+
+Step 3: 비교 분석
+├─ 기존: Trades X, PF 0.89, PnL A
+├─ MTF: Trades Y, PF ?, PnL B
+├─ 개선도: (PF_new - 0.89) / 0.89 = ?%
+
+출력:
+결과를 테이블 형식으로 정렬
+│ 구분 │ Trades │ Win Rate │ PF │ PnL │ 개선율 │
+└─────────────────────────────────────────
--- a/docs/plans/2026-04-21-mtf-oos-dryrun-result.md
+++ b/docs/plans/2026-04-21-mtf-oos-dryrun-result.md
@@ -0,0 +1,40 @@
+# MTF Pullback Bot OOS Dry-run 중간 보고
+
+## 가설
+MTF Pullback Bot의 멀티타임프레임 풀백 시그널이 XRPUSDT LONG/SHORT 양방향에서 수익을 낸다.
+
+## 데이터
+- 심볼: XRPUSDT
+- 기간: 2026-04-02 ~ 2026-04-20 (19일)
+- 거래 수: 24건 (LONG 17, SHORT 7) — 목표 50건 미달
+- 테스트 마감: 2026-04-30
+
+## 중간 결과
+
+### 방향별 상세 (Raw, 수수료 미반영)
+
+| 방향 | 거래 수 | 승률 | PF | CumPnL(bps) | 평균보유 |
+|------|---------|------|----|-------------|---------|
+| Total | 24 | 41.7% | 0.98 | -15.8 | 240m |
+| LONG | 17 | 47.1% | 1.17 | +103.1 | 277m |
+| SHORT | 7 | 28.6% | 0.58 | -118.9 | 150m |
+
+### 비용 보정 시나리오
+
+| 시나리오 | Total PF | Total CumPnL | LONG PF | SHORT PF |
+|----------|----------|-------------|---------|----------|
+| fees_only | 0.79 | -207.8 | 0.95 | 0.46 |
+| realistic | 0.74 | -264.8 | 0.90 | 0.42 |
+| pessimistic | 0.66 | -369.8 | 0.80 | 0.37 |
+
+## 현재 상태
+
+**판단 불가** — 거래 수 24건 < 50건 기준, 테스트 기간 잔여 9일 (4/30 마감)
+
+### 우려 사항 (최종 판정 시 확인 필요)
+- SHORT 승률 28.6%, PF 0.58 — 역 edge 가능성
+- Raw PF 0.98 — 수수료 미반영으로도 손익분기 미달
+- LONG은 Raw PF 1.17이나 수수료 반영 시 PF 0.95로 하락
+
+## 결론
+4/30 마감 후 50건 이상 누적 시 최종 판정 예정.
--- a/docs/plans/2026-05-04-mtf-btc-filter-design.md
+++ b/docs/plans/2026-05-04-mtf-btc-filter-design.md
@@ -0,0 +1,79 @@
+# MTF + BTC 추세 필터 백테스트 설계
+
+## 가설
+
+BTC 추세 방향과 일치하는 MTF 풀백 시그널만 실행하면 비용 반영 후에도 PF > 1.2를 달성한다.
+
+## 메인 가설 (사전 확정 — commitment device)
+
+> 메인 가설은 sweep 결과를 보기 **전에** BTC 1h + EMA 50/200 + ADX > 20으로 확정한다.
+> sweep 12개 결과에서 가장 좋은 조합으로 사후 변경하지 않는다.
+> 4h/1d 결과는 robustness 참고용이며, 메인 가설이 OOS 실패 시
+> "다른 조합이 됐으니 PASS"로 구제하지 않는다.
+
+- **BTC 타임프레임**: 1h
+- **BTC EMA**: fast=50, slow=200
+- **BTC ADX 임계값**: 20
+- **선택 근거**: XRP MTF bot의 1h 메타필터와 동일 기준 → 시그널 정합성 확보, 사후 정당화 차단
+
+## 필터 로직
+
+```
+BTC_trend = (BTC EMA_fast > BTC EMA_slow) AND (BTC ADX > 20)
+    ? (EMA_fast > EMA_slow ? "UP" : "DOWN")
+    : "NEUTRAL"
+
+if BTC_trend == "UP":    SHORT 차단, LONG만 허용
+if BTC_trend == "DOWN":  LONG 차단, SHORT만 허용
+if BTC_trend == "NEUTRAL": 양방향 차단 (추세 불명확)
+```
+
+## Sweep 파라미터 (robustness check용)
+
+| 파라미터 | 후보 | 설명 |
+|---------|------|------|
+| BTC 타임프레임 | 1h, 4h, 1d | BTC 추세 판단 주기 |
+| BTC EMA fast | 20, 50 | 단기 EMA |
+| BTC EMA slow | 100, 200 | 장기 EMA |
+
+총 조합: 3 × 2 × 2 = 12개. ADX > 20은 전 조합 고정.
+
+## 데이터
+
+- XRP: `data/xrpusdt/combined_15m.parquet` (기존)
+- BTC: `data/btcusdt/combined_15m.parquet` (fetch 필요)
+- 기간: 최소 6개월 (XRP와 동일 기간)
+- BTC 15m → 1h/4h/1d resample 후 EMA/ADX 계산
+- merge: `merge_asof(direction="backward")` — look-ahead bias 방지
+- fetch 후 XRP/BTC 첫/마지막 timestamp + bar 수 일치 검증 필수
+
+## IS/OOS 분할
+
+- 앞 70% IS, 뒤 30% OOS (단순 시간 분할)
+- ML 없고 sweep 12개뿐이므로 walk-forward 불필요
+
+## 합격 기준
+
+| 기준 | 값 | 비고 |
+|------|-----|------|
+| 메인 가설 OOS fees_only PF | >= 1.2 | 실거래 마진 확보 |
+| 메인 가설 OOS realistic PF | >= 1.0 | 슬리피지+펀딩 반영 후 흑자 |
+| LONG/SHORT 양쪽 fees_only PF | >= 0.8 | 대칭성 |
+| OOS 거래 수 | >= 50 | 통계적 유의성 |
+| IS/OOS PF 격차 | < 30% | 과적합 방지 |
+| 베이스라인 대비 OOS PF | 명확한 개선 | 절대값보다 차이 중요 |
+| IS 거래 수 | >= 100 | 미달 시 조합 자동 제외 |
+
+## 판정 흐름
+
+1. 베이스라인(BTC 필터 없는 MTF) IS/OOS 결과 먼저 산출
+2. 12개 조합 IS sweep, 모두 결과 저장 (IS 거래 수 < 100 자동 제외)
+3. 메인 가설(1h/EMA50-200/ADX20) OOS 검증 → 합격 기준 통과 시 PASS
+4. 나머지 11개도 OOS 검증 → robustness 보고서 (참고용)
+5. 메인 가설 실패 시 → 전략 폐기 (다른 조합으로 구제 안 함)
+
+## 산출물
+
+- `scripts/mtf_btc_filter_backtest.py` — 백테스트 스크립트
+- `docs/plans/2026-05-04-mtf-btc-filter-result.md` — 결과 문서
+- 거래 수준 로그 (CSV) — entry/exit/BTC trend/PnL 포함, 사후 분석용
--- a/docs/plans/2026-05-04-mtf-btc-filter-result.md
+++ b/docs/plans/2026-05-04-mtf-btc-filter-result.md
@@ -0,0 +1,80 @@
+# MTF + BTC 추세 필터 백테스트 결과
+
+## 가설
+
+BTC 추세 방향과 일치하는 MTF 풀백 시그널만 실행하면 비용 반영 후에도 PF > 1.2를 달성한다.
+
+메인 가설 (사전 확정): BTC 1h + EMA 50/200 + ADX > 20
+
+## 데이터
+
+- 심볼: XRPUSDT
+- 기간: 2024-04-02 ~ 2026-05-03 (761일, 73,123 bars)
+- IS: 2024-04-02 ~ 2025-09-17 (70%)
+- OOS: 2025-09-17 ~ 2026-05-03 (30%)
+- BTC OHLCV: XRP parquet 내 상관 컬럼 활용 (NaN 0%)
+
+## 베이스라인 (BTC 필터 없음)
+
+| 구분 | IS PF(fees) | OOS PF(fees) | OOS 거래수 |
+|------|------------|-------------|-----------|
+| Total | 1.02 | 0.94 | 206 |
+| LONG | 1.04 | 0.71 | 69 |
+| SHORT | 1.01 | 1.06 | 137 |
+
+베이스라인 자체가 OOS에서 적자 (fees PF 0.94).
+
+## 메인 가설 결과 (BTC 1h EMA50/200 ADX>20)
+
+| 구분 | IS PF(fees) | OOS PF(fees) | OOS PF(real) | OOS 거래수 |
+|------|------------|-------------|-------------|-----------|
+| Total | 1.12 | **0.90** | 0.88 | 158 |
+| LONG | 1.24 | 0.81 | 0.78 | 56 |
+| SHORT | 1.02 | 0.95 | 0.92 | 102 |
+
+## 합격 기준 체크
+
+| 기준 | 결과 | 판정 |
+|------|------|------|
+| OOS fees_only PF >= 1.2 | 0.90 | **FAIL** |
+| OOS realistic PF >= 1.0 | 0.88 | **FAIL** |
+| OOS 거래수 >= 50 | 158 | PASS |
+| LONG/SHORT fees PF >= 0.8 | L:0.81 S:0.95 | PASS |
+| IS/OOS PF 격차 < 30% | 19.6% | PASS |
+| 베이스라인 대비 개선 | 0.90 vs 0.94 | **FAIL** |
+
+## Sweep Robustness
+
+| 조합 | IS N | IS FPF | OOS FPF | OOS rPF | 비고 |
+|------|------|--------|---------|---------|------|
+| BTC_1h_EMA20/100 | 327 | 1.19 | 0.84 | 0.81 | |
+| BTC_1h_EMA20/200 | 333 | 1.16 | 0.86 | 0.84 | |
+| BTC_1h_EMA50/100 | 335 | 1.14 | 0.83 | 0.80 | |
+| **BTC_1h_EMA50/200** | **333** | **1.12** | **0.90** | **0.88** | **메인 ★** |
+| BTC_4h_EMA20/100 | 310 | 1.00 | 1.04 | 1.01 | |
+| BTC_4h_EMA20/200 | 269 | 0.95 | 1.09 | 1.06 | |
+| BTC_4h_EMA50/100 | 271 | 0.91 | 1.07 | 1.04 | |
+| BTC_4h_EMA50/200 | 231 | 0.91 | 1.01 | 0.98 | |
+| BTC_1d_EMA20/100 | 151 | 1.10 | 1.17 | 1.13 | |
+| BTC_1d_EMA20/200 | 94 | 1.41 | 1.28 | 1.25 | IS<100 SKIP |
+| BTC_1d_EMA50/100 | 129 | 1.28 | 1.20 | 1.16 | |
+| BTC_1d_EMA50/200 | 96 | 1.44 | 1.14 | 1.11 | IS<100 SKIP |
+
+- 1h 조합: **전멸** (OOS fees PF 0.83~0.90)
+- 4h 조합: 1.01~1.09 — BEP 수준, 1.2 미달
+- 1d 조합: 1.17~1.28 — 겉보기 좋으나 IS 거래수 94~151로 과적합 위험 + 사전 합의에 의해 구제 불가
+
+12개 중 fees PF >= 1.2 통과는 **1개** (BTC_1d_EMA20/100, 1.17로 미달 → 실제 0개).
+
+## 핵심 발견
+
+1. **BTC 필터가 성과를 악화시킴**: 메인 가설 OOS PF 0.90 < 베이스라인 0.94. 필터가 오히려 좋은 거래를 걸러냄
+2. **IS/OOS 격차 패턴**: 1h 조합은 IS에서 과적합(1.12~1.19) → OOS 붕괴(0.83~0.90). 전형적 curve-fitting
+3. **1d가 좋아보이는 함정**: IS 거래수가 94~151로 적어 통계적 유의성 부족. 사전 합의대로 구제 불가
+4. **MTF Pullback 자체의 한계**: 베이스라인 OOS 0.94로 전략 자체에 edge 없음. 필터로 보완 불가능
+
+## 결론
+
+**FAIL** — MTF Pullback 전략 최종 폐기.
+
+BTC 추세 필터(1h EMA50/200 ADX>20)는 OOS에서 베이스라인보다 오히려 악화. 12개 sweep 조합 중 합격 기준(fees PF >= 1.2)을 통과한 조합 0개. 베이스라인 자체도 OOS 적자(PF 0.94)로 전략의 근본적 edge 부재 확인.
--- a/docs/plans/2026-05-04-mtf-oos-final-result.md
+++ b/docs/plans/2026-05-04-mtf-oos-final-result.md
@@ -0,0 +1,48 @@
+# MTF Pullback Bot OOS Dry-run 최종 결과
+
+## 가설
+MTF Pullback Bot의 멀티타임프레임 풀백 시그널이 XRPUSDT LONG/SHORT 양방향에서 수익을 낸다.
+
+## 데이터
+- 심볼: XRPUSDT
+- 기간: 2026-04-02 ~ 2026-04-29 (28일)
+- 거래 수: 30건 (LONG 18, SHORT 12)
+- 실제 자금 투입: 0 (dry-run, 시그널+주문 기록만)
+
+## 결과
+
+### Raw (비용 미반영, 참고용)
+
+| 방향 | 거래 수 | 승률 | PF | CumPnL(bps) | 평균보유 |
+|------|---------|------|----|-------------|---------|
+| Total | 30 | 43.3% | 1.06 | +61.6 | 237m |
+| LONG | 18 | 50.0% | 1.28 | +167.7 | 272m |
+| SHORT | 12 | 33.3% | 0.73 | -106.1 | 185m |
+
+### 비용 보정 시나리오
+
+| 시나리오 | Total PF | Total CumPnL | LONG PF | SHORT PF |
+|----------|----------|-------------|---------|----------|
+| fees_only | 0.84 | -178.4 | 1.04 | 0.56 |
+| realistic | 0.79 | -250.4 | 0.98 | 0.52 |
+| pessimistic | 0.69 | -382.4 | 0.87 | 0.45 |
+
+### 4/21 중간 보고 대비 변화
+
+| 지표 | 중간(24건) | 최종(30건) |
+|------|-----------|-----------|
+| Raw Total PF | 0.98 | 1.06 |
+| fees_only Total PF | 0.79 | 0.84 |
+| SHORT Raw PF | 0.58 | 0.73 |
+| SHORT fees_only PF | 0.46 | 0.56 |
+
+마지막 6건에서 소폭 개선됐으나 구조적 문제(SHORT 역 edge, 비용 흡수 불가) 불변.
+
+## 결론
+
+**FAIL** — 폐기 사유 2개 해당:
+
+1. **OOS PF < 1.0 (비용 반영)**: fees_only 시나리오에서도 PF 0.84, 수수료를 이길 수 없음
+2. **LONG/SHORT 대칭성 실패**: SHORT Raw PF 0.73 — 전략 자체에 SHORT edge 없음
+
+Raw PF 1.06은 수수료(taker 왕복 8bps)를 흡수하기엔 마진이 너무 얇음. LONG만 분리 운영해도 fees_only PF 1.04로 거래 비용 감당 불가.
--- a/docs/plans/2026-05-04-strategy-post-mortem.md
+++ b/docs/plans/2026-05-04-strategy-post-mortem.md
@@ -0,0 +1,133 @@
+# CoinTrader 전략 Post-Mortem (2026-05-04)
+
+지금까지 시도한 모든 전략의 실패 원인을 분석하고, 다음 방향을 도출한다.
+
+## 1. 사망자 명단
+
+| # | 전략 | 기간 | IS PF | OOS PF(fees) | 사망 원인 |
+|---|------|------|-------|-------------|----------|
+| 1 | RSI+MACD+BB+EMA+StochRSI (기본) | 2026-03 | — | 0.89 | 수익성 부족 |
+| 2 | ML Filter (LightGBM/ONNX) | 2026-03 | — | ML OFF > ML ON | 피처에 alpha 없음 |
+| 3 | LS Ratio | 2026-03 | — | 0.86 (best) | r=0.12, 비용 커버 불가 |
+| 4 | FR × OI | 2026-03 | — | SHORT 1.88 / LONG 0.50 | 대칭성 실패 |
+| 5 | Taker Buy/Sell Ratio | 2026-03 | — | 0.93 | r=-0.08, 약함 |
+| 6 | MTF Pullback (OOS dry-run) | 2026-04 | — | 0.84 (fees) | SHORT 역 edge |
+| 7 | MTF Pullback + BTC 필터 | 2026-05 | 1.12 | 0.90 (fees) | 베이스라인보다 악화 |
+
+**7전 7패.** 단 하나도 비용 반영 후 OOS PF > 1.0을 달성하지 못함.
+
+## 2. 공통 실패 패턴
+
+### 패턴 A: "IS에서 살고 OOS에서 죽는다"
+
+| 전략 | IS fees PF | OOS fees PF | 격차 |
+|------|-----------|-------------|------|
+| 기본 시그널 | ~1.02 | 0.89 | -13% |
+| MTF Pullback | 1.02 | 0.94 | -8% |
+| MTF + BTC 1h | 1.12 | 0.90 | -20% |
+
+IS에서 마진이 얇은 전략(PF 1.0~1.1)은 OOS에서 비용을 이기지 못한다. **IS PF < 1.3이면 OOS 통과 가능성 거의 0.**
+
+### 패턴 B: "LONG/SHORT 중 한쪽만 작동"
+
+| 전략 | 좋은 쪽 | 나쁜 쪽 | 진단 |
+|------|---------|---------|------|
+| FR × OI | SHORT PF 1.88 | LONG PF 0.50 | 시장 베타 |
+| MTF OOS (4월) | LONG PF 1.28 | SHORT PF 0.73 | 상승장 편승 |
+| MTF 백테스트 OOS | SHORT PF 1.06 | LONG PF 0.71 | 하락장 편승 |
+
+한쪽만 좋은 건 "전략의 edge"가 아니라 **해당 기간의 시장 방향(beta)**을 타고 있을 뿐. 기간이 바뀌면 좋은 쪽과 나쁜 쪽이 뒤집힌다 (4월 OOS에서 LONG이 좋았고, 전체 백테스트 OOS에서는 SHORT가 좋았음).
+
+### 패턴 C: "필터/피처를 추가할수록 악화"
+
+| 레이어 | OOS fees PF |
+|--------|-------------|
+| 기본 시그널 | 0.89 |
+| + ML Filter | 더 나빠짐 |
+| MTF Pullback (베이스라인) | 0.94 |
+| + BTC 추세 필터 | 0.90 (악화) |
+
+필터를 추가하면 **좋은 거래도 같이 걸러진다**. 기본 시그널 자체에 edge가 없으면 필터로 구제 불가능. 오히려 거래 수 감소 → 통계적 불안정 → 악화.
+
+## 3. 근본 원인 진단: Edge 부재 vs Regime Dependence?
+
+**답: 둘 다. 그리고 이 둘은 연결되어 있다.**
+
+1. **Edge 부재가 근본**: RSI/MACD/BB/EMA/StochRSI + 풀백 패턴은 너무 많은 참가자가 아는 시그널. 알파가 소진된 공공재. r < 0.15인 시그널은 수수료 8bps를 이길 수 없다.
+
+2. **Regime dependence는 결과**: edge가 없는 전략은 시장 방향(beta)에 수익이 좌우된다. 상승장에선 LONG이, 하락장에선 SHORT가 좋아 보이지만 이건 전략의 alpha가 아니라 시장의 beta.
+
+3. **검증 방법론은 정상 작동**: IS/OOS 분할, 비용 모델, 대칭성 체크, 사전 가설 확정 — 이 프레임워크가 7개 전략을 정확히 거부했다. 문제는 방법론이 아니라 **시그널 소스**.
+
+## 4. "뭘 안 시도했나?" — 미탐색 영역 지도
+
+### 이미 소진한 영역 (재시도 금지)
+
+- Binance 공개 API 파생 피처 (전수 테스트 완료)
+- 기술적 지표 조합 (RSI, MACD, BB, EMA, StochRSI, ADX)
+- ML 피처 선택/앙상블 (LightGBM, ONNX — 피처 자체에 alpha 없음)
+- 시간대 변경 (15m→1h→4h→1d sweep 완료)
+- 상관 자산 필터 (BTC 추세 필터 검증 완료)
+
+### 미탐색 영역
+
+| 방향 | 구체적 아이디어 | 난이도 | 기대값 |
+|------|---------------|--------|--------|
+| **데이터 소스 변경** | 온체인 (whale wallet, exchange flow) | 높음 | 중 — 지연 있으나 독점 정보 가능성 |
+| **데이터 소스 변경** | 크로스 거래소 (OKX/Bybit OI/FR 차이) | 중 | 중 — 차이 자체가 시그널 |
+| **데이터 소스 변경** | 소셜/뉴스 센티먼트 | 높음 | 낮음 — 노이즈 많음, 지연 |
+| **자산 변경** | BTC/ETH (유동성 높은 메이저) | 낮음 | 중 — 경쟁 치열하지만 유동성 풍부 |
+| **자산 변경** | 저유동성 알트 (DYDX, APE 등) | 낮음 | 중 — 비효율성 클 수 있으나 슬리피지 |
+| **패러다임 변경** | 통계적 차익 (pair trading, mean reversion) | 중 | 중상 — 방향 중립, beta 제거 |
+| **패러다임 변경** | 마이크로 구조 (호가창 불균형, 체결 패턴) | 높음 | 높음 — 진입 장벽이 alpha 보호 |
+| **패러다임 변경** | 변동성 전략 (vol expansion/compression) | 중 | 중 — 방향 아닌 "크기" 예측 |
+| **실행 최적화** | 동일 시그널 + maker order (비용 절감) | 중 | 중 — 0.08%→0.04% 비용 반감 |
+
+## 5. 다음 방향 제안
+
+### 우선순위 1: 패러다임을 바꿔라
+
+지금까지의 모든 전략은 **"방향 예측"** 패러다임:
+- "XRP가 오를까 내릴까?" → LONG/SHORT
+
+이 패러다임에서 공개 시그널로 alpha를 찾기는 극히 어렵다. 대안:
+
+**(A) 통계적 차익 (Stat Arb / Pair Trading)**
+- XRP/BTC 비율의 평균 회귀
+- 여러 알트코인 간 상대 강도 기반 롱숏
+- 장점: 방향 중립 → beta 제거, 대칭성 자동 충족
+- 인프라: 현재 multi-symbol 아키텍처로 확장 가능
+
+**(B) 변동성 전략**
+- "방향"이 아니라 "크기"를 예측
+- ATR 수축 → 확장 시 양방향 진입 (straddle-like)
+- BB squeeze → breakout 방향은 예측하되, 비용 대비 마진이 큰 구간만
+
+### 우선순위 2: 비용을 줄여라
+
+현재 taker 왕복 8bps가 모든 전략의 적. 같은 시그널이라도:
+- Entry를 limit order로 → 4bps 절감 (왕복 4bps)
+- 이것만으로 MTF 베이스라인 OOS가 0.94 → ~1.02로 개선 가능
+- 근본 해결은 아니지만, 마진이 얇은 전략을 BEP 위로 올릴 수 있음
+
+### 우선순위 3: 데이터 소스를 넓혀라
+
+Binance 공개 API는 소진. 외부 데이터가 필요:
+- Glassnode/CryptoQuant (온체인)
+- 크로스 거래소 OI/FR 차이
+- 이 데이터는 접근 비용(유료 API)이 있으나 그만큼 경쟁자가 적음
+
+## 6. 보존할 자산
+
+7전 7패였지만 **인프라는 자산**:
+
+| 자산 | 용도 |
+|------|------|
+| 비용 모델 (3 시나리오) | 어떤 전략이든 재사용 |
+| IS/OOS 검증 프레임워크 | 자기기만 방지 |
+| 사전 가설 확정 프로토콜 | sweep 과적합 방지 |
+| multi-symbol 아키텍처 | pair trading 확장 가능 |
+| kill switch (Fast/Slow) | 실전 리스크 관리 |
+| 주간 리포트 파이프라인 | 모니터링 |
+
+다음 전략이 뭐든, 이 검증 인프라 위에서 시작하면 실패를 빠르게 확인할 수 있다.
--- a/models/dogeusdt/lgbm_filter.pkl
+++ b/models/dogeusdt/lgbm_filter.pkl
--- a/models/dogeusdt/lgbm_filter_prev.pkl
+++ b/models/dogeusdt/lgbm_filter_prev.pkl
--- a/models/dogeusdt/training_log.json
+++ b/models/dogeusdt/training_log.json
@@ -98,5 +98,30 @@
      "reg_lambda": 0.000157
    },
    "weight_scale": 1.783105
+  },
+  {
+    "date": "2026-03-21T19:04:07.386894",
+    "backend": "lgbm",
+    "auc": 0.9251,
+    "best_threshold": 0.3743,
+    "best_precision": 0.467,
+    "best_recall": 0.208,
+    "samples": 12172,
+    "features": 26,
+    "time_weight_decay": 2.0,
+    "model_path": "models/dogeusdt/lgbm_filter.pkl",
+    "tuned_params_path": null,
+    "lgbm_params": {
+      "n_estimators": 434,
+      "learning_rate": 0.123659,
+      "max_depth": 6,
+      "num_leaves": 14,
+      "min_child_samples": 10,
+      "subsample": 0.929062,
+      "colsample_bytree": 0.94633,
+      "reg_alpha": 0.573971,
+      "reg_lambda": 0.000157
+    },
+    "weight_scale": 1.783105
  }
 ]
--- a/models/solusdt/lgbm_filter.pkl
+++ b/models/solusdt/lgbm_filter.pkl
--- a/models/solusdt/training_log.json
+++ b/models/solusdt/training_log.json
@@ -0,0 +1,27 @@
+[
+  {
+    "date": "2026-03-21T19:04:06.511618",
+    "backend": "lgbm",
+    "auc": 0.9185,
+    "best_threshold": 0.4455,
+    "best_precision": 0.418,
+    "best_recall": 0.444,
+    "samples": 11772,
+    "features": 26,
+    "time_weight_decay": 2.0,
+    "model_path": "models/solusdt/lgbm_filter.pkl",
+    "tuned_params_path": null,
+    "lgbm_params": {
+      "n_estimators": 434,
+      "learning_rate": 0.123659,
+      "max_depth": 6,
+      "num_leaves": 14,
+      "min_child_samples": 10,
+      "subsample": 0.929062,
+      "colsample_bytree": 0.94633,
+      "reg_alpha": 0.573971,
+      "reg_lambda": 0.000157
+    },
+    "weight_scale": 1.783105
+  }
+]
--- a/models/xrpusdt/lgbm_filter.pkl
+++ b/models/xrpusdt/lgbm_filter.pkl
--- a/models/xrpusdt/lgbm_filter_prev.pkl
+++ b/models/xrpusdt/lgbm_filter_prev.pkl
--- a/models/xrpusdt/training_log.json
+++ b/models/xrpusdt/training_log.json
@@ -98,5 +98,30 @@
      "reg_lambda": 0.000157
    },
    "weight_scale": 1.783105
+  },
+  {
+    "date": "2026-03-21T19:04:05.287371",
+    "backend": "lgbm",
+    "auc": 0.9237,
+    "best_threshold": 0.5306,
+    "best_precision": 0.494,
+    "best_recall": 0.303,
+    "samples": 12156,
+    "features": 26,
+    "time_weight_decay": 2.0,
+    "model_path": "models/xrpusdt/lgbm_filter.pkl",
+    "tuned_params_path": null,
+    "lgbm_params": {
+      "n_estimators": 434,
+      "learning_rate": 0.123659,
+      "max_depth": 6,
+      "num_leaves": 14,
+      "min_child_samples": 10,
+      "subsample": 0.929062,
+      "colsample_bytree": 0.94633,
+      "reg_alpha": 0.573971,
+      "reg_lambda": 0.000157
+    },
+    "weight_scale": 1.783105
  }
 ]
--- a/results/dogeusdt/ml_comparison_20260321_195841.json
+++ b/results/dogeusdt/ml_comparison_20260321_195841.json
@@ -0,0 +1,44 @@
+{
+  "timestamp": "2026-03-21T19:58:41.732033",
+  "symbols": [
+    "DOGEUSDT"
+  ],
+  "ml_off": {
+    "total_trades": 322,
+    "total_pnl": -1547.342,
+    "return_pct": -154.73,
+    "win_rate": 31.37,
+    "avg_win": 44.161,
+    "avg_loss": -27.1837,
+    "payoff_ratio": 1.62,
+    "max_consecutive_losses": 9,
+    "profit_factor": 0.74,
+    "max_drawdown_pct": 155.09,
+    "sharpe_ratio": -23.72,
+    "total_fees": 891.5776,
+    "close_reasons": {
+      "STOP_LOSS": 198,
+      "REVERSE_SIGNAL": 58,
+      "TAKE_PROFIT": 66
+    }
+  },
+  "ml_on": {
+    "total_trades": 20,
+    "total_pnl": -173.2651,
+    "return_pct": -17.33,
+    "win_rate": 35.0,
+    "avg_win": 42.0257,
+    "avg_loss": -35.9573,
+    "payoff_ratio": 1.17,
+    "max_consecutive_losses": 3,
+    "profit_factor": 0.63,
+    "max_drawdown_pct": 18.86,
+    "sharpe_ratio": -40.35,
+    "total_fees": 77.1422,
+    "close_reasons": {
+      "STOP_LOSS": 13,
+      "REVERSE_SIGNAL": 4,
+      "TAKE_PROFIT": 3
+    }
+  }
+}
--- a/results/dogeusdt/ml_comparison_20260321_200334.json
+++ b/results/dogeusdt/ml_comparison_20260321_200334.json
@@ -0,0 +1,45 @@
+{
+  "timestamp": "2026-03-21T20:03:34.650022",
+  "symbols": [
+    "DOGEUSDT"
+  ],
+  "ml_off": {
+    "total_trades": 40,
+    "total_pnl": 161.0802,
+    "return_pct": 16.11,
+    "win_rate": 25.0,
+    "avg_win": 107.1017,
+    "avg_loss": -30.3312,
+    "payoff_ratio": 3.53,
+    "max_consecutive_losses": 8,
+    "profit_factor": 1.18,
+    "max_drawdown_pct": 22.19,
+    "sharpe_ratio": 7.08,
+    "total_fees": 150.4991,
+    "close_reasons": {
+      "STOP_LOSS": 25,
+      "REVERSE_SIGNAL": 8,
+      "END_OF_DATA": 1,
+      "TAKE_PROFIT": 6
+    }
+  },
+  "ml_on": {
+    "total_trades": 47,
+    "total_pnl": -285.0131,
+    "return_pct": -28.5,
+    "win_rate": 34.04,
+    "avg_win": 61.4296,
+    "avg_loss": -40.8996,
+    "payoff_ratio": 1.5,
+    "max_consecutive_losses": 7,
+    "profit_factor": 0.78,
+    "max_drawdown_pct": 40.93,
+    "sharpe_ratio": -21.03,
+    "total_fees": 176.3033,
+    "close_reasons": {
+      "STOP_LOSS": 30,
+      "REVERSE_SIGNAL": 6,
+      "TAKE_PROFIT": 11
+    }
+  }
+}
--- a/results/dogeusdt/wf_backtest_20260318_232112.json
+++ b/results/dogeusdt/wf_backtest_20260318_232112.json
--- a/results/dogeusdt/wf_backtest_20260321_194418.json
+++ b/results/dogeusdt/wf_backtest_20260321_194418.json
@@ -0,0 +1,188 @@
+{
+  "mode": "walk_forward",
+  "config": {
+    "symbols": [
+      "DOGEUSDT"
+    ],
+    "start": null,
+    "end": null,
+    "initial_balance": 1000.0,
+    "leverage": 10,
+    "fee_pct": 0.04,
+    "slippage_pct": 0.01,
+    "use_ml": true,
+    "ml_threshold": 0.55,
+    "max_daily_loss_pct": 0.05,
+    "max_positions": 3,
+    "max_same_direction": 2,
+    "margin_max_ratio": 0.5,
+    "margin_min_ratio": 0.2,
+    "margin_decay_rate": 0.0006,
+    "atr_sl_mult": 1.5,
+    "atr_tp_mult": 3.0,
+    "min_notional": 5.0,
+    "signal_threshold": 3,
+    "adx_threshold": 0,
+    "volume_multiplier": 1.5,
+    "train_months": 6,
+    "test_months": 1,
+    "time_weight_decay": 2.0,
+    "negative_ratio": 3
+  },
+  "summary": {
+    "total_trades": 2,
+    "total_pnl": -84.5014,
+    "return_pct": -8.45,
+    "win_rate": 0.0,
+    "avg_win": 0.0,
+    "avg_loss": -42.2507,
+    "payoff_ratio": 0.0,
+    "max_consecutive_losses": 2,
+    "profit_factor": 0.0,
+    "max_drawdown_pct": 4.28,
+    "sharpe_ratio": -5831.15,
+    "total_fees": 7.8265,
+    "close_reasons": {
+      "STOP_LOSS": 2
+    }
+  },
+  "folds": [
+    {
+      "fold": 1,
+      "train_period": "2025-03-05 ~ 2025-09-05",
+      "test_period": "2025-09-05 ~ 2025-10-05",
+      "summary": {
+        "total_trades": 2,
+        "total_pnl": -84.5014,
+        "return_pct": -8.45,
+        "win_rate": 0.0,
+        "avg_win": 0.0,
+        "avg_loss": -42.2507,
+        "payoff_ratio": 0.0,
+        "max_consecutive_losses": 2,
+        "profit_factor": 0.0,
+        "max_drawdown_pct": 4.28,
+        "sharpe_ratio": -5831.15,
+        "total_fees": 7.8265,
+        "close_reasons": {
+          "STOP_LOSS": 2
+        }
+      }
+    }
+  ],
+  "trades": [
+    {
+      "symbol": "DOGEUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-10-03 14:00:00",
+      "exit_time": "2025-10-03 14:30:00",
+      "entry_price": 0.253975,
+      "exit_price": 0.255986,
+      "quantity": 19685.0,
+      "sl": 0.255986,
+      "tp": 0.249952,
+      "gross_pnl": -39.591591,
+      "entry_fee": 1.999796,
+      "exit_fee": 2.015633,
+      "net_pnl": -43.60702,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": 0.6215,
+      "indicators": {
+        "rsi": 39.31265367759862,
+        "macd_hist": -9.917203695834255e-06,
+        "atr": 0.001340837894829163,
+        "adx": 22.11118870853989
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "DOGEUSDT",
+      "side": "LONG",
+      "entry_time": "2025-10-04 02:00:00",
+      "exit_time": "2025-10-04 03:00:00",
+      "entry_price": 0.254255,
+      "exit_price": 0.252284,
+      "quantity": 18809.6,
+      "sl": 0.252284,
+      "tp": 0.258198,
+      "gross_pnl": -37.083263,
+      "entry_fee": 1.912977,
+      "exit_fee": 1.898144,
+      "net_pnl": -40.894384,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": 0.589,
+      "indicators": {
+        "rsi": 29.729826487088012,
+        "macd_hist": -0.0004551413936173264,
+        "atr": 0.0013143381729553857,
+        "adx": 17.29524723775582
+      },
+      "fold": 1
+    }
+  ],
+  "validation": {
+    "overall": "FAIL",
+    "checks": [
+      {
+        "name": "exit_after_entry",
+        "passed": true,
+        "level": "FAIL",
+        "message": "모든 트레이드에서 청산 > 진입"
+      },
+      {
+        "name": "sl_tp_direction",
+        "passed": true,
+        "level": "FAIL",
+        "message": "SL/TP 방향 정합"
+      },
+      {
+        "name": "no_overlap",
+        "passed": true,
+        "level": "FAIL",
+        "message": "포지션 비중첩 확인"
+      },
+      {
+        "name": "positive_fees",
+        "passed": true,
+        "level": "FAIL",
+        "message": "수수료 양수 확인"
+      },
+      {
+        "name": "no_negative_balance",
+        "passed": true,
+        "level": "FAIL",
+        "message": "잔고 양수 유지"
+      },
+      {
+        "name": "win_rate_high",
+        "passed": true,
+        "level": "WARNING",
+        "message": "승률 정상 (0.0%)"
+      },
+      {
+        "name": "win_rate_low",
+        "passed": false,
+        "level": "WARNING",
+        "message": "승률 0.0% < 20% — 신호 로직 반전 의심"
+      },
+      {
+        "name": "mdd_nonzero",
+        "passed": true,
+        "level": "WARNING",
+        "message": "MDD 정상 (4.3%)"
+      },
+      {
+        "name": "trade_frequency",
+        "passed": false,
+        "level": "WARNING",
+        "message": "월 평균 2.0건 < 5건 — 신호 생성 부족"
+      },
+      {
+        "name": "profit_factor_high",
+        "passed": true,
+        "level": "WARNING",
+        "message": "PF 정상 (0.00)"
+      }
+    ]
+  }
+}
--- a/results/solusdt/ml_comparison_20260321_195841.json
+++ b/results/solusdt/ml_comparison_20260321_195841.json
@@ -0,0 +1,44 @@
+{
+  "timestamp": "2026-03-21T19:58:41.166218",
+  "symbols": [
+    "SOLUSDT"
+  ],
+  "ml_off": {
+    "total_trades": 346,
+    "total_pnl": -1287.9804,
+    "return_pct": -128.8,
+    "win_rate": 33.82,
+    "avg_win": 35.5174,
+    "avg_loss": -23.7708,
+    "payoff_ratio": 1.49,
+    "max_consecutive_losses": 11,
+    "profit_factor": 0.76,
+    "max_drawdown_pct": 176.42,
+    "sharpe_ratio": -20.59,
+    "total_fees": 940.6664,
+    "close_reasons": {
+      "STOP_LOSS": 187,
+      "TAKE_PROFIT": 68,
+      "REVERSE_SIGNAL": 91
+    }
+  },
+  "ml_on": {
+    "total_trades": 14,
+    "total_pnl": 80.7573,
+    "return_pct": 8.08,
+    "win_rate": 35.71,
+    "avg_win": 72.906,
+    "avg_loss": -31.5303,
+    "payoff_ratio": 2.31,
+    "max_consecutive_losses": 4,
+    "profit_factor": 1.28,
+    "max_drawdown_pct": 11.46,
+    "sharpe_ratio": 18.5,
+    "total_fees": 51.8491,
+    "close_reasons": {
+      "STOP_LOSS": 7,
+      "TAKE_PROFIT": 5,
+      "REVERSE_SIGNAL": 2
+    }
+  }
+}
--- a/results/solusdt/ml_comparison_20260321_200332.json
+++ b/results/solusdt/ml_comparison_20260321_200332.json
@@ -0,0 +1,45 @@
+{
+  "timestamp": "2026-03-21T20:03:32.481740",
+  "symbols": [
+    "SOLUSDT"
+  ],
+  "ml_off": {
+    "total_trades": 31,
+    "total_pnl": -3218.5412,
+    "return_pct": -321.85,
+    "win_rate": 25.81,
+    "avg_win": 40.6328,
+    "avg_loss": -154.0697,
+    "payoff_ratio": 0.26,
+    "max_consecutive_losses": 7,
+    "profit_factor": 0.09,
+    "max_drawdown_pct": 333.12,
+    "sharpe_ratio": -39.57,
+    "total_fees": 112.8457,
+    "close_reasons": {
+      "STOP_LOSS": 21,
+      "TAKE_PROFIT": 5,
+      "REVERSE_SIGNAL": 4,
+      "END_OF_DATA": 1
+    }
+  },
+  "ml_on": {
+    "total_trades": 17,
+    "total_pnl": -488.3431,
+    "return_pct": -48.83,
+    "win_rate": 11.76,
+    "avg_win": 79.5151,
+    "avg_loss": -43.1582,
+    "payoff_ratio": 1.84,
+    "max_consecutive_losses": 8,
+    "profit_factor": 0.25,
+    "max_drawdown_pct": 45.94,
+    "sharpe_ratio": -123.73,
+    "total_fees": 61.1816,
+    "close_reasons": {
+      "STOP_LOSS": 14,
+      "REVERSE_SIGNAL": 1,
+      "TAKE_PROFIT": 2
+    }
+  }
+}
--- a/results/solusdt/wf_backtest_20260321_194417.json
+++ b/results/solusdt/wf_backtest_20260321_194417.json
@@ -0,0 +1,81 @@
+{
+  "mode": "walk_forward",
+  "config": {
+    "symbols": [
+      "SOLUSDT"
+    ],
+    "start": null,
+    "end": null,
+    "initial_balance": 1000.0,
+    "leverage": 10,
+    "fee_pct": 0.04,
+    "slippage_pct": 0.01,
+    "use_ml": true,
+    "ml_threshold": 0.55,
+    "max_daily_loss_pct": 0.05,
+    "max_positions": 3,
+    "max_same_direction": 2,
+    "margin_max_ratio": 0.5,
+    "margin_min_ratio": 0.2,
+    "margin_decay_rate": 0.0006,
+    "atr_sl_mult": 1.5,
+    "atr_tp_mult": 3.0,
+    "min_notional": 5.0,
+    "signal_threshold": 3,
+    "adx_threshold": 0,
+    "volume_multiplier": 1.5,
+    "train_months": 6,
+    "test_months": 1,
+    "time_weight_decay": 2.0,
+    "negative_ratio": 3
+  },
+  "summary": {
+    "total_trades": 0,
+    "total_pnl": 0.0,
+    "return_pct": 0.0,
+    "win_rate": 0.0,
+    "avg_win": 0.0,
+    "avg_loss": 0.0,
+    "payoff_ratio": 0.0,
+    "max_consecutive_losses": 0,
+    "profit_factor": 0.0,
+    "max_drawdown_pct": 0.0,
+    "sharpe_ratio": 0.0,
+    "total_fees": 0.0,
+    "close_reasons": {}
+  },
+  "folds": [
+    {
+      "fold": 1,
+      "train_period": "2025-03-18 ~ 2025-09-18",
+      "test_period": "2025-09-18 ~ 2025-10-18",
+      "summary": {
+        "total_trades": 0,
+        "total_pnl": 0.0,
+        "return_pct": 0.0,
+        "win_rate": 0.0,
+        "avg_win": 0.0,
+        "avg_loss": 0.0,
+        "payoff_ratio": 0.0,
+        "max_consecutive_losses": 0,
+        "profit_factor": 0.0,
+        "max_drawdown_pct": 0.0,
+        "sharpe_ratio": 0.0,
+        "total_fees": 0.0,
+        "close_reasons": {}
+      }
+    }
+  ],
+  "trades": [],
+  "validation": {
+    "overall": "PASS",
+    "checks": [
+      {
+        "name": "trade_count",
+        "passed": true,
+        "level": "FAIL",
+        "message": "트레이드 없음 (검증 스킵)"
+      }
+    ]
+  }
+}
--- a/results/weekly/report_2026-03-22.html
+++ b/results/weekly/report_2026-03-22.html
--- a/results/weekly/report_2026-03-22.json
+++ b/results/weekly/report_2026-03-22.json
--- a/results/weekly/report_2026-03-29.html
+++ b/results/weekly/report_2026-03-29.html
--- a/results/weekly/report_2026-03-29.json
+++ b/results/weekly/report_2026-03-29.json
--- a/results/weekly/report_2026-04-05.html
+++ b/results/weekly/report_2026-04-05.html
--- a/results/weekly/report_2026-04-05.json
+++ b/results/weekly/report_2026-04-05.json
--- a/results/weekly/report_2026-04-12.html
+++ b/results/weekly/report_2026-04-12.html
--- a/results/weekly/report_2026-04-12.json
+++ b/results/weekly/report_2026-04-12.json
--- a/results/weekly/report_2026-04-19.html
+++ b/results/weekly/report_2026-04-19.html
--- a/results/weekly/report_2026-04-19.json
+++ b/results/weekly/report_2026-04-19.json
--- a/results/weekly/report_2026-04-26.html
+++ b/results/weekly/report_2026-04-26.html
--- a/results/weekly/report_2026-04-26.json
+++ b/results/weekly/report_2026-04-26.json
--- a/results/weekly/report_2026-05-03.html
+++ b/results/weekly/report_2026-05-03.html
--- a/results/weekly/report_2026-05-03.json
+++ b/results/weekly/report_2026-05-03.json
--- a/results/xrpusdt/backtest_20260322_224712.json
+++ b/results/xrpusdt/backtest_20260322_224712.json
@@ -0,0 +1,549 @@
+{
+  "config": {
+    "symbols": [
+      "XRPUSDT"
+    ],
+    "start": null,
+    "end": null,
+    "initial_balance": 1000.0,
+    "leverage": 20,
+    "fee_pct": 0.04,
+    "slippage_pct": 0.01,
+    "use_ml": false,
+    "ml_threshold": 0.55,
+    "max_daily_loss_pct": 0.05,
+    "max_positions": 3,
+    "max_same_direction": 2,
+    "margin_max_ratio": 0.5,
+    "margin_min_ratio": 0.2,
+    "margin_decay_rate": 0.0006,
+    "atr_sl_mult": 1.5,
+    "atr_tp_mult": 4.0,
+    "min_notional": 5.0,
+    "signal_threshold": 3,
+    "adx_threshold": 25.0,
+    "volume_multiplier": 2.5
+  },
+  "summary": {
+    "total_trades": 19,
+    "total_pnl": -90.5608,
+    "return_pct": -9.06,
+    "win_rate": 31.58,
+    "avg_win": 187.773,
+    "avg_loss": -93.6307,
+    "payoff_ratio": 2.01,
+    "max_consecutive_losses": 8,
+    "profit_factor": 0.93,
+    "max_drawdown_pct": 39.26,
+    "sharpe_ratio": -6.38,
+    "total_fees": 130.2737,
+    "close_reasons": {
+      "STOP_LOSS": 13,
+      "TAKE_PROFIT": 6
+    }
+  },
+  "trades": [
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-03-26 13:45:00",
+      "exit_time": "2025-03-26 14:30:00",
+      "entry_price": 2.415342,
+      "exit_price": 2.399559,
+      "quantity": 4140.6,
+      "sl": 2.399559,
+      "tp": 2.457429,
+      "gross_pnl": -65.350891,
+      "entry_fee": 4.000385,
+      "exit_fee": 3.974245,
+      "net_pnl": -73.325521,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 26.92729946174303,
+        "macd_hist": -0.004175927274053651,
+        "atr": 0.010521967932285681,
+        "adx": 28.1934914013265
+      }
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-03-29 09:30:00",
+      "exit_time": "2025-03-29 13:00:00",
+      "entry_price": 2.091091,
+      "exit_price": 2.117184,
+      "quantity": 4431.1,
+      "sl": 2.117184,
+      "tp": 2.02151,
+      "gross_pnl": -115.619197,
+      "entry_fee": 3.706333,
+      "exit_fee": 3.752581,
+      "net_pnl": -123.07811,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 29.5299317993386,
+        "macd_hist": -0.0016272252554855211,
+        "atr": 0.017395108299016367,
+        "adx": 35.60495925685308
+      }
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-04-02 02:00:00",
+      "exit_time": "2025-04-02 05:45:00",
+      "entry_price": 2.090609,
+      "exit_price": 2.070463,
+      "quantity": 3844.2,
+      "sl": 2.070463,
+      "tp": 2.144332,
+      "gross_pnl": -77.446201,
+      "entry_fee": 3.214688,
+      "exit_fee": 3.183709,
+      "net_pnl": -83.844598,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 29.415272650543557,
+        "macd_hist": -0.0038881862305720294,
+        "atr": 0.013430831024751285,
+        "adx": 26.024817307471817
+      }
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-04-03 12:15:00",
+      "exit_time": "2025-04-03 14:45:00",
+      "entry_price": 2.016898,
+      "exit_price": 1.956939,
+      "quantity": 3568.3,
+      "sl": 2.039383,
+      "tp": 1.956939,
+      "gross_pnl": 213.952202,
+      "entry_fee": 2.878759,
+      "exit_fee": 2.793178,
+      "net_pnl": 208.280264,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 39.0031761939588,
+        "macd_hist": -0.00027555783529762453,
+        "atr": 0.01498978519243727,
+        "adx": 29.63100718549373
+      }
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-04-06 18:45:00",
+      "exit_time": "2025-04-06 20:30:00",
+      "entry_price": 1.994699,
+      "exit_price": 1.968556,
+      "quantity": 4653.0,
+      "sl": 1.968556,
+      "tp": 2.064416,
+      "gross_pnl": -121.647028,
+      "entry_fee": 3.712535,
+      "exit_fee": 3.663876,
+      "net_pnl": -129.023439,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 21.033027596614833,
+        "macd_hist": -0.006740564223060543,
+        "atr": 0.01742918952793266,
+        "adx": 42.14016267928252
+      }
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-04-08 12:00:00",
+      "exit_time": "2025-04-08 16:15:00",
+      "entry_price": 1.952805,
+      "exit_price": 1.879673,
+      "quantity": 4091.2,
+      "sl": 1.980229,
+      "tp": 1.879673,
+      "gross_pnl": 299.197837,
+      "entry_fee": 3.195726,
+      "exit_fee": 3.076047,
+      "net_pnl": 292.926065,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 73.41350187407278,
+        "macd_hist": 0.010090522420784207,
+        "atr": 0.01828301215814375,
+        "adx": 26.85765122231918
+      }
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-04-09 01:00:00",
+      "exit_time": "2025-04-09 01:45:00",
+      "entry_price": 1.737226,
+      "exit_price": 1.775195,
+      "quantity": 5591.5,
+      "sl": 1.775195,
+      "tp": 1.635978,
+      "gross_pnl": -212.299611,
+      "entry_fee": 3.88548,
+      "exit_fee": 3.9704,
+      "net_pnl": -220.155491,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 27.2339289074866,
+        "macd_hist": -0.002023427338529095,
+        "atr": 0.025312183439683184,
+        "adx": 47.62708053828556
+      }
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-04-12 13:00:00",
+      "exit_time": "2025-04-12 13:30:00",
+      "entry_price": 2.085709,
+      "exit_price": 2.123429,
+      "quantity": 4180.2,
+      "sl": 2.071563,
+      "tp": 2.123429,
+      "gross_pnl": 157.679154,
+      "entry_fee": 3.487472,
+      "exit_fee": 3.550543,
+      "net_pnl": 150.641139,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 71.08975614304354,
+        "macd_hist": 0.0004691893650785872,
+        "atr": 0.009430120184239851,
+        "adx": 41.039203834939215
+      }
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-04-22 13:15:00",
+      "exit_time": "2025-04-22 14:00:00",
+      "entry_price": 2.105411,
+      "exit_price": 2.137638,
+      "quantity": 4726.0,
+      "sl": 2.093325,
+      "tp": 2.137638,
+      "gross_pnl": 152.30925,
+      "entry_fee": 3.980068,
+      "exit_fee": 4.040992,
+      "net_pnl": 144.28819,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 57.841977820073645,
+        "macd_hist": 4.316762016507922e-06,
+        "atr": 0.008056985291244722,
+        "adx": 27.486954266795543
+      }
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-04-24 08:30:00",
+      "exit_time": "2025-04-24 13:30:00",
+      "entry_price": 2.129213,
+      "exit_price": 2.178907,
+      "quantity": 4383.8,
+      "sl": 2.110578,
+      "tp": 2.178907,
+      "gross_pnl": 217.849236,
+      "entry_fee": 3.733617,
+      "exit_fee": 3.820757,
+      "net_pnl": 210.294862,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 24.016950832949433,
+        "macd_hist": -0.003143540248224934,
+        "atr": 0.012423538716450883,
+        "adx": 45.63982334493204
+      }
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-04-26 07:30:00",
+      "exit_time": "2025-04-26 09:00:00",
+      "entry_price": 2.235676,
+      "exit_price": 2.198258,
+      "quantity": 3372.4,
+      "sl": 2.249708,
+      "tp": 2.198258,
+      "gross_pnl": 126.188433,
+      "entry_fee": 3.015838,
+      "exit_fee": 2.965363,
+      "net_pnl": 120.207233,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 76.71113426509163,
+        "macd_hist": 0.005320482189513192,
+        "atr": 0.009354497780232585,
+        "adx": 30.700551675430855
+      }
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-04-28 07:15:00",
+      "exit_time": "2025-04-28 07:45:00",
+      "entry_price": 2.314669,
+      "exit_price": 2.333953,
+      "quantity": 2608.7,
+      "sl": 2.333953,
+      "tp": 2.263244,
+      "gross_pnl": -50.306622,
+      "entry_fee": 2.41531,
+      "exit_fee": 2.435433,
+      "net_pnl": -55.157366,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 73.98848696551217,
+        "macd_hist": 0.0034538468677465604,
+        "atr": 0.012856115408039817,
+        "adx": 27.89133838050565
+      }
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-04-30 07:45:00",
+      "exit_time": "2025-04-30 12:30:00",
+      "entry_price": 2.219022,
+      "exit_price": 2.205478,
+      "quantity": 3051.6,
+      "sl": 2.205478,
+      "tp": 2.255138,
+      "gross_pnl": -41.329913,
+      "entry_fee": 2.708627,
+      "exit_fee": 2.692095,
+      "net_pnl": -46.730634,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 33.11711659050469,
+        "macd_hist": -0.0028131165153663005,
+        "atr": 0.00902912407526822,
+        "adx": 27.47479838290321
+      }
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-04-30 13:15:00",
+      "exit_time": "2025-04-30 13:30:00",
+      "entry_price": 2.173717,
+      "exit_price": 2.152862,
+      "quantity": 3374.3,
+      "sl": 2.152862,
+      "tp": 2.229333,
+      "gross_pnl": -70.373501,
+      "entry_fee": 2.93391,
+      "exit_fee": 2.90576,
+      "net_pnl": -76.213172,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 27.513370415814684,
+        "macd_hist": -0.006240527006868588,
+        "atr": 0.013903822313270735,
+        "adx": 31.23141348514888
+      }
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-05-05 01:30:00",
+      "exit_time": "2025-05-05 02:15:00",
+      "entry_price": 2.139986,
+      "exit_price": 2.153598,
+      "quantity": 3803.3,
+      "sl": 2.153598,
+      "tp": 2.103686,
+      "gross_pnl": -51.77209,
+      "entry_fee": 3.255603,
+      "exit_fee": 3.276312,
+      "net_pnl": -58.304005,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 30.413570034116045,
+        "macd_hist": -0.0010637135478183844,
+        "atr": 0.009074941875769175,
+        "adx": 26.27401092812825
+      }
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-05-17 01:15:00",
+      "exit_time": "2025-05-17 01:45:00",
+      "entry_price": 2.335133,
+      "exit_price": 2.31116,
+      "quantity": 3709.9,
+      "sl": 2.31116,
+      "tp": 2.399062,
+      "gross_pnl": -88.937959,
+      "entry_fee": 3.465245,
+      "exit_fee": 3.42967,
+      "net_pnl": -95.832873,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 28.536979724863077,
+        "macd_hist": -0.004501483267526404,
+        "atr": 0.01598209455229851,
+        "adx": 51.966384578102044
+      }
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-05-18 14:30:00",
+      "exit_time": "2025-05-18 15:45:00",
+      "entry_price": 2.427557,
+      "exit_price": 2.442135,
+      "quantity": 3848.5,
+      "sl": 2.442135,
+      "tp": 2.388682,
+      "gross_pnl": -56.104255,
+      "entry_fee": 3.736982,
+      "exit_fee": 3.759423,
+      "net_pnl": -63.60066,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 73.26480732687115,
+        "macd_hist": 0.0028537582643641994,
+        "atr": 0.009718809144697027,
+        "adx": 29.42506362068419
+      }
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-05-20 12:30:00",
+      "exit_time": "2025-05-20 17:00:00",
+      "entry_price": 2.330967,
+      "exit_price": 2.345796,
+      "quantity": 4149.8,
+      "sl": 2.345796,
+      "tp": 2.291423,
+      "gross_pnl": -61.53732,
+      "entry_fee": 3.869219,
+      "exit_fee": 3.893833,
+      "net_pnl": -69.300372,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 33.11852309537045,
+        "macd_hist": -0.0003174284393988123,
+        "atr": 0.009885989673296352,
+        "adx": 34.742890662078324
+      }
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-05-23 12:15:00",
+      "exit_time": "2025-05-23 22:45:00",
+      "entry_price": 2.340634,
+      "exit_price": 2.313574,
+      "quantity": 4240.1,
+      "sl": 2.313574,
+      "tp": 2.412795,
+      "gross_pnl": -114.738573,
+      "entry_fee": 3.969809,
+      "exit_fee": 3.923914,
+      "net_pnl": -122.632296,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 18.100631569972105,
+        "macd_hist": -0.011460760086984913,
+        "atr": 0.018040230723781962,
+        "adx": 33.73789035029933
+      }
+    }
+  ],
+  "validation": {
+    "overall": "PASS",
+    "checks": [
+      {
+        "name": "exit_after_entry",
+        "passed": true,
+        "level": "FAIL",
+        "message": "모든 트레이드에서 청산 > 진입"
+      },
+      {
+        "name": "sl_tp_direction",
+        "passed": true,
+        "level": "FAIL",
+        "message": "SL/TP 방향 정합"
+      },
+      {
+        "name": "no_overlap",
+        "passed": true,
+        "level": "FAIL",
+        "message": "포지션 비중첩 확인"
+      },
+      {
+        "name": "positive_fees",
+        "passed": true,
+        "level": "FAIL",
+        "message": "수수료 양수 확인"
+      },
+      {
+        "name": "no_negative_balance",
+        "passed": true,
+        "level": "FAIL",
+        "message": "잔고 양수 유지"
+      },
+      {
+        "name": "win_rate_high",
+        "passed": true,
+        "level": "WARNING",
+        "message": "승률 정상 (31.6%)"
+      },
+      {
+        "name": "win_rate_low",
+        "passed": true,
+        "level": "WARNING",
+        "message": "승률 정상 (31.6%)"
+      },
+      {
+        "name": "mdd_nonzero",
+        "passed": true,
+        "level": "WARNING",
+        "message": "MDD 정상 (39.3%)"
+      },
+      {
+        "name": "trade_frequency",
+        "passed": true,
+        "level": "WARNING",
+        "message": "월 평균 10.0건"
+      },
+      {
+        "name": "profit_factor_high",
+        "passed": true,
+        "level": "WARNING",
+        "message": "PF 정상 (0.93)"
+      }
+    ]
+  }
+}
--- a/results/xrpusdt/ml_comparison_20260321_195840.json
+++ b/results/xrpusdt/ml_comparison_20260321_195840.json
@@ -0,0 +1,45 @@
+{
+  "timestamp": "2026-03-21T19:58:40.087843",
+  "symbols": [
+    "XRPUSDT"
+  ],
+  "ml_off": {
+    "total_trades": 362,
+    "total_pnl": -1076.1058,
+    "return_pct": -107.61,
+    "win_rate": 36.74,
+    "avg_win": 30.9612,
+    "avg_loss": -22.681,
+    "payoff_ratio": 1.37,
+    "max_consecutive_losses": 8,
+    "profit_factor": 0.79,
+    "max_drawdown_pct": 117.67,
+    "sharpe_ratio": -18.8,
+    "total_fees": 1094.0448,
+    "close_reasons": {
+      "STOP_LOSS": 202,
+      "TAKE_PROFIT": 74,
+      "REVERSE_SIGNAL": 84,
+      "END_OF_DATA": 2
+    }
+  },
+  "ml_on": {
+    "total_trades": 14,
+    "total_pnl": 2.0995,
+    "return_pct": 0.21,
+    "win_rate": 35.71,
+    "avg_win": 38.8329,
+    "avg_loss": -21.3406,
+    "payoff_ratio": 1.82,
+    "max_consecutive_losses": 6,
+    "profit_factor": 1.01,
+    "max_drawdown_pct": 11.88,
+    "sharpe_ratio": 0.74,
+    "total_fees": 54.5343,
+    "close_reasons": {
+      "STOP_LOSS": 7,
+      "REVERSE_SIGNAL": 4,
+      "TAKE_PROFIT": 3
+    }
+  }
+}
--- a/results/xrpusdt/ml_comparison_20260321_200332.json
+++ b/results/xrpusdt/ml_comparison_20260321_200332.json
@@ -0,0 +1,44 @@
+{
+  "timestamp": "2026-03-21T20:03:32.712401",
+  "symbols": [
+    "XRPUSDT"
+  ],
+  "ml_off": {
+    "total_trades": 53,
+    "total_pnl": 121.6625,
+    "return_pct": 12.17,
+    "win_rate": 43.4,
+    "avg_win": 39.0003,
+    "avg_loss": -25.8448,
+    "payoff_ratio": 1.51,
+    "max_consecutive_losses": 8,
+    "profit_factor": 1.16,
+    "max_drawdown_pct": 25.63,
+    "sharpe_ratio": 11.94,
+    "total_fees": 181.3167,
+    "close_reasons": {
+      "STOP_LOSS": 30,
+      "TAKE_PROFIT": 15,
+      "REVERSE_SIGNAL": 8
+    }
+  },
+  "ml_on": {
+    "total_trades": 40,
+    "total_pnl": -256.2189,
+    "return_pct": -25.62,
+    "win_rate": 35.0,
+    "avg_win": 44.2545,
+    "avg_loss": -33.6839,
+    "payoff_ratio": 1.31,
+    "max_consecutive_losses": 11,
+    "profit_factor": 0.71,
+    "max_drawdown_pct": 36.87,
+    "sharpe_ratio": -27.75,
+    "total_fees": 151.8982,
+    "close_reasons": {
+      "STOP_LOSS": 21,
+      "REVERSE_SIGNAL": 10,
+      "TAKE_PROFIT": 9
+    }
+  }
+}
--- a/results/xrpusdt/mtf_btc_filter_trades.csv
+++ b/results/xrpusdt/mtf_btc_filter_trades.csv
--- a/results/xrpusdt/strategy_sweep_20260329_142440.json
+++ b/results/xrpusdt/strategy_sweep_20260329_142440.json
--- a/results/xrpusdt/wf_backtest_20260318_232111.json
+++ b/results/xrpusdt/wf_backtest_20260318_232111.json
@@ -0,0 +1,835 @@
+{
+  "mode": "walk_forward",
+  "config": {
+    "symbols": [
+      "XRPUSDT"
+    ],
+    "start": null,
+    "end": null,
+    "initial_balance": 1000.0,
+    "leverage": 10,
+    "fee_pct": 0.04,
+    "slippage_pct": 0.01,
+    "use_ml": false,
+    "ml_threshold": 0.55,
+    "max_daily_loss_pct": 0.05,
+    "max_positions": 3,
+    "max_same_direction": 2,
+    "margin_max_ratio": 0.5,
+    "margin_min_ratio": 0.2,
+    "margin_decay_rate": 0.0006,
+    "atr_sl_mult": 2.0,
+    "atr_tp_mult": 2.0,
+    "min_notional": 5.0,
+    "signal_threshold": 3,
+    "adx_threshold": 25.0,
+    "volume_multiplier": 2.5,
+    "train_months": 3,
+    "test_months": 1,
+    "time_weight_decay": 2.0,
+    "negative_ratio": 5
+  },
+  "summary": {
+    "total_trades": 27,
+    "total_pnl": 217.0703,
+    "return_pct": 21.71,
+    "win_rate": 66.67,
+    "avg_win": 33.2223,
+    "avg_loss": -42.3256,
+    "payoff_ratio": 0.78,
+    "max_consecutive_losses": 3,
+    "profit_factor": 1.57,
+    "max_drawdown_pct": 11.99,
+    "sharpe_ratio": 33.32,
+    "total_fees": 102.7825,
+    "close_reasons": {
+      "STOP_LOSS": 9,
+      "TAKE_PROFIT": 18
+    }
+  },
+  "folds": [
+    {
+      "fold": 1,
+      "train_period": "2025-03-05 ~ 2025-06-05",
+      "test_period": "2025-06-05 ~ 2025-07-05",
+      "summary": {
+        "total_trades": 9,
+        "total_pnl": -54.288,
+        "return_pct": -5.43,
+        "win_rate": 44.44,
+        "avg_win": 40.6662,
+        "avg_loss": -43.3906,
+        "payoff_ratio": 0.94,
+        "max_consecutive_losses": 3,
+        "profit_factor": 0.75,
+        "max_drawdown_pct": 11.99,
+        "sharpe_ratio": -21.46,
+        "total_fees": 32.8699,
+        "close_reasons": {
+          "STOP_LOSS": 5,
+          "TAKE_PROFIT": 4
+        }
+      }
+    },
+    {
+      "fold": 2,
+      "train_period": "2025-06-05 ~ 2025-09-05",
+      "test_period": "2025-09-05 ~ 2025-10-05",
+      "summary": {
+        "total_trades": 10,
+        "total_pnl": 13.0734,
+        "return_pct": 1.31,
+        "win_rate": 60.0,
+        "avg_win": 29.5084,
+        "avg_loss": -40.9943,
+        "payoff_ratio": 0.72,
+        "max_consecutive_losses": 3,
+        "profit_factor": 1.08,
+        "max_drawdown_pct": 10.97,
+        "sharpe_ratio": 5.62,
+        "total_fees": 39.3346,
+        "close_reasons": {
+          "TAKE_PROFIT": 6,
+          "STOP_LOSS": 4
+        }
+      }
+    },
+    {
+      "fold": 3,
+      "train_period": "2025-09-05 ~ 2025-12-05",
+      "test_period": "2025-12-05 ~ 2026-01-05",
+      "summary": {
+        "total_trades": 8,
+        "total_pnl": 258.2849,
+        "return_pct": 25.83,
+        "win_rate": 100.0,
+        "avg_win": 32.2856,
+        "avg_loss": 0.0,
+        "payoff_ratio": "Infinity",
+        "max_consecutive_losses": 0,
+        "profit_factor": "Infinity",
+        "max_drawdown_pct": 0.0,
+        "sharpe_ratio": 502.51,
+        "total_fees": 30.578,
+        "close_reasons": {
+          "TAKE_PROFIT": 8
+        }
+      }
+    }
+  ],
+  "trades": [
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-06-12 11:15:00",
+      "exit_time": "2025-06-12 13:00:00",
+      "entry_price": 2.223978,
+      "exit_price": 2.237955,
+      "quantity": 2248.0,
+      "sl": 2.237955,
+      "tp": 2.21,
+      "gross_pnl": -31.420573,
+      "entry_fee": 1.999801,
+      "exit_fee": 2.012369,
+      "net_pnl": -35.432743,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 26.97199737318929,
+        "macd_hist": -0.0007807103280135859,
+        "atr": 0.006988561711463904,
+        "adx": 43.4578914382015
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-06-12 20:30:00",
+      "exit_time": "2025-06-13 00:00:00",
+      "entry_price": 2.186419,
+      "exit_price": 2.163885,
+      "quantity": 2201.5,
+      "sl": 2.163885,
+      "tp": 2.208952,
+      "gross_pnl": -49.607437,
+      "entry_fee": 1.92536,
+      "exit_fee": 1.905517,
+      "net_pnl": -53.438315,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 26.41519543415668,
+        "macd_hist": -0.005495027011351469,
+        "atr": 0.011266735681191995,
+        "adx": 35.41443548413551
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-06-16 22:30:00",
+      "exit_time": "2025-06-16 23:45:00",
+      "entry_price": 2.260826,
+      "exit_price": 2.231631,
+      "quantity": 2006.6,
+      "sl": 2.231631,
+      "tp": 2.290021,
+      "gross_pnl": -58.582699,
+      "entry_fee": 1.814629,
+      "exit_fee": 1.791196,
+      "net_pnl": -62.188525,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 33.211506920436555,
+        "macd_hist": -0.007666291215691772,
+        "atr": 0.014597503086660083,
+        "adx": 41.77057022158849
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-06-17 15:00:00",
+      "exit_time": "2025-06-17 15:30:00",
+      "entry_price": 2.188781,
+      "exit_price": 2.164935,
+      "quantity": 1926.0,
+      "sl": 2.212627,
+      "tp": 2.164935,
+      "gross_pnl": 45.926824,
+      "entry_fee": 1.686237,
+      "exit_fee": 1.667866,
+      "net_pnl": 42.572721,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 35.98442517376965,
+        "macd_hist": -0.000473160901783975,
+        "atr": 0.011922851577807921,
+        "adx": 31.230008994240638
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-06-21 13:30:00",
+      "exit_time": "2025-06-21 15:15:00",
+      "entry_price": 2.119112,
+      "exit_price": 2.109684,
+      "quantity": 2086.2,
+      "sl": 2.109684,
+      "tp": 2.128539,
+      "gross_pnl": -19.667423,
+      "entry_fee": 1.768356,
+      "exit_fee": 1.76049,
+      "net_pnl": -23.196269,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 29.460371663394117,
+        "macd_hist": -0.002291006577745399,
+        "atr": 0.0047136955379463,
+        "adx": 26.139853452702802
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-06-21 21:15:00",
+      "exit_time": "2025-06-21 21:30:00",
+      "entry_price": 2.045995,
+      "exit_price": 2.018384,
+      "quantity": 2099.3,
+      "sl": 2.073607,
+      "tp": 2.018384,
+      "gross_pnl": 57.964484,
+      "entry_fee": 1.718063,
+      "exit_fee": 1.694877,
+      "net_pnl": 54.551543,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 24.112041978961905,
+        "macd_hist": -0.0015821538372272313,
+        "atr": 0.013805669484335523,
+        "adx": 47.020225174544926
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-06-24 05:30:00",
+      "exit_time": "2025-06-24 06:00:00",
+      "entry_price": 2.184818,
+      "exit_price": 2.207587,
+      "quantity": 2087.2,
+      "sl": 2.16205,
+      "tp": 2.207587,
+      "gross_pnl": 47.522393,
+      "entry_fee": 1.824061,
+      "exit_fee": 1.84307,
+      "net_pnl": 43.855261,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 73.02163697288638,
+        "macd_hist": 0.0005479493365071683,
+        "atr": 0.011384245075129916,
+        "adx": 47.36536786932758
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-07-01 13:00:00",
+      "exit_time": "2025-07-01 14:15:00",
+      "entry_price": 2.185781,
+      "exit_price": 2.203594,
+      "quantity": 2182.0,
+      "sl": 2.203594,
+      "tp": 2.167969,
+      "gross_pnl": -38.866074,
+      "entry_fee": 1.90775,
+      "exit_fee": 1.923296,
+      "net_pnl": -42.697121,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 34.25494593254047,
+        "macd_hist": -0.00014675405719808375,
+        "atr": 0.008906066514248343,
+        "adx": 38.40722178323835
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-07-04 06:00:00",
+      "exit_time": "2025-07-04 07:30:00",
+      "entry_price": 2.232877,
+      "exit_price": 2.220445,
+      "quantity": 2036.1,
+      "sl": 2.245309,
+      "tp": 2.220445,
+      "gross_pnl": 25.312421,
+      "entry_fee": 1.818544,
+      "exit_fee": 1.808419,
+      "net_pnl": 21.685458,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 31.442919224174045,
+        "macd_hist": -0.00029321477558042104,
+        "atr": 0.0062159081353788895,
+        "adx": 33.56850119916028
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-05 19:45:00",
+      "exit_time": "2025-09-05 21:00:00",
+      "entry_price": 2.863514,
+      "exit_price": 2.839468,
+      "quantity": 1745.9,
+      "sl": 2.887559,
+      "tp": 2.839468,
+      "gross_pnl": 41.980567,
+      "entry_fee": 1.999763,
+      "exit_fee": 1.982971,
+      "net_pnl": 37.997832,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 66.8667614741176,
+        "macd_hist": 0.005566660638547516,
+        "atr": 0.012022614930199287,
+        "adx": 25.794325095274626
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-07 07:30:00",
+      "exit_time": "2025-09-07 13:30:00",
+      "entry_price": 2.831483,
+      "exit_price": 2.839182,
+      "quantity": 1750.6,
+      "sl": 2.823784,
+      "tp": 2.839182,
+      "gross_pnl": 13.478415,
+      "entry_fee": 1.982718,
+      "exit_fee": 1.988109,
+      "net_pnl": 9.507588,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 70.72939012092385,
+        "macd_hist": 0.00013947818915852105,
+        "atr": 0.0038496557346203194,
+        "adx": 25.87514662158794
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-07 14:15:00",
+      "exit_time": "2025-09-07 17:45:00",
+      "entry_price": 2.888611,
+      "exit_price": 2.863658,
+      "quantity": 1711.8,
+      "sl": 2.913564,
+      "tp": 2.863658,
+      "gross_pnl": 42.714942,
+      "entry_fee": 1.97789,
+      "exit_fee": 1.960804,
+      "net_pnl": 38.776248,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 76.27147788789821,
+        "macd_hist": 0.006331113894477991,
+        "atr": 0.012476615713124774,
+        "adx": 29.135371839765913
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-09 07:00:00",
+      "exit_time": "2025-09-09 08:30:00",
+      "entry_price": 3.009099,
+      "exit_price": 3.032748,
+      "quantity": 1621.9,
+      "sl": 3.032748,
+      "tp": 2.98545,
+      "gross_pnl": -38.356788,
+      "entry_fee": 1.952183,
+      "exit_fee": 1.967526,
+      "net_pnl": -42.276497,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 73.38194905544675,
+        "macd_hist": 0.006160466326798137,
+        "atr": 0.011824646391069867,
+        "adx": 28.105801823891394
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-12 20:45:00",
+      "exit_time": "2025-09-12 21:30:00",
+      "entry_price": 3.121788,
+      "exit_price": 3.09291,
+      "quantity": 1587.4,
+      "sl": 3.150665,
+      "tp": 3.09291,
+      "gross_pnl": 45.839824,
+      "entry_fee": 1.98221,
+      "exit_fee": 1.963874,
+      "net_pnl": 41.893739,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 78.88995114530964,
+        "macd_hist": 0.004793783646225545,
+        "atr": 0.014438649390670705,
+        "adx": 33.848649235778474
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-14 11:15:00",
+      "exit_time": "2025-09-14 12:30:00",
+      "entry_price": 3.066993,
+      "exit_price": 3.050039,
+      "quantity": 1594.0,
+      "sl": 3.083947,
+      "tp": 3.050039,
+      "gross_pnl": 27.024629,
+      "entry_fee": 1.955515,
+      "exit_fee": 1.944705,
+      "net_pnl": 23.124409,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 31.419480021379645,
+        "macd_hist": -0.0003629091436070245,
+        "atr": 0.008476985221720718,
+        "adx": 31.882046477112183
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-20 14:00:00",
+      "exit_time": "2025-09-20 15:00:00",
+      "entry_price": 2.971603,
+      "exit_price": 2.984114,
+      "quantity": 1630.7,
+      "sl": 2.984114,
+      "tp": 2.959092,
+      "gross_pnl": -20.401941,
+      "entry_fee": 1.938317,
+      "exit_fee": 1.946478,
+      "net_pnl": -24.286736,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 36.09553473183674,
+        "macd_hist": -0.00018720159437711752,
+        "atr": 0.006255577606168083,
+        "adx": 28.84076206692945
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-24 19:45:00",
+      "exit_time": "2025-09-24 21:45:00",
+      "entry_price": 2.976198,
+      "exit_price": 2.948913,
+      "quantity": 1646.2,
+      "sl": 2.948913,
+      "tp": 3.003482,
+      "gross_pnl": -44.915196,
+      "entry_fee": 1.959767,
+      "exit_fee": 1.941801,
+      "net_pnl": -48.816763,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 77.25608496751632,
+        "macd_hist": 0.00019635721897620986,
+        "atr": 0.013642083686890932,
+        "adx": 66.36435142210216
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-25 12:15:00",
+      "exit_time": "2025-09-25 12:30:00",
+      "entry_price": 2.793221,
+      "exit_price": 2.81825,
+      "quantity": 1781.8,
+      "sl": 2.81825,
+      "tp": 2.768191,
+      "gross_pnl": -44.597807,
+      "entry_fee": 1.990784,
+      "exit_fee": 2.008623,
+      "net_pnl": -48.597214,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 27.256149561284357,
+        "macd_hist": -0.0005773233003328118,
+        "atr": 0.012514818420656685,
+        "adx": 36.706433983392714
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-28 22:00:00",
+      "exit_time": "2025-09-29 02:15:00",
+      "entry_price": 2.850785,
+      "exit_price": 2.868214,
+      "quantity": 1700.7,
+      "sl": 2.833356,
+      "tp": 2.868214,
+      "gross_pnl": 29.641341,
+      "entry_fee": 1.939332,
+      "exit_fee": 1.951189,
+      "net_pnl": 25.750821,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 69.94607598871028,
+        "macd_hist": 0.0002172037763433672,
+        "atr": 0.008714453238038499,
+        "adx": 45.96715774504039
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-12-10 10:30:00",
+      "exit_time": "2025-12-10 14:30:00",
+      "entry_price": 2.069993,
+      "exit_price": 2.056326,
+      "quantity": 2415.2,
+      "sl": 2.08366,
+      "tp": 2.056326,
+      "gross_pnl": 33.009596,
+      "entry_fee": 1.999779,
+      "exit_fee": 1.986575,
+      "net_pnl": 29.023242,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 37.038012691554805,
+        "macd_hist": -9.211636302669133e-05,
+        "atr": 0.0068337189344636114,
+        "adx": 28.943927763667713
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-12-12 16:00:00",
+      "exit_time": "2025-12-12 18:30:00",
+      "entry_price": 1.988899,
+      "exit_price": 2.013001,
+      "quantity": 2498.4,
+      "sl": 1.964797,
+      "tp": 2.013001,
+      "gross_pnl": 60.216838,
+      "entry_fee": 1.987626,
+      "exit_fee": 2.011713,
+      "net_pnl": 56.2175,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 28.182013495720106,
+        "macd_hist": -0.00643391832048344,
+        "atr": 0.01205108033747697,
+        "adx": 30.769786891839054
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-12-19 13:15:00",
+      "exit_time": "2025-12-19 13:45:00",
+      "entry_price": 1.878712,
+      "exit_price": 1.863781,
+      "quantity": 2596.8,
+      "sl": 1.893643,
+      "tp": 1.863781,
+      "gross_pnl": 38.773597,
+      "entry_fee": 1.951456,
+      "exit_fee": 1.935946,
+      "net_pnl": 34.886195,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 68.16547032772114,
+        "macd_hist": -4.5929936914913816e-05,
+        "atr": 0.007465649526915487,
+        "adx": 40.69667585881617
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-12-25 23:30:00",
+      "exit_time": "2025-12-26 02:00:00",
+      "entry_price": 1.831783,
+      "exit_price": 1.844712,
+      "quantity": 2624.8,
+      "sl": 1.818854,
+      "tp": 1.844712,
+      "gross_pnl": 33.936201,
+      "entry_fee": 1.923226,
+      "exit_fee": 1.9368,
+      "net_pnl": 30.076175,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 18.688435627302994,
+        "macd_hist": -0.0034657628634239823,
+        "atr": 0.006464530874639477,
+        "adx": 30.228290924248867
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2026-01-01 15:45:00",
+      "exit_time": "2026-01-01 17:15:00",
+      "entry_price": 1.861986,
+      "exit_price": 1.870892,
+      "quantity": 2543.8,
+      "sl": 1.853081,
+      "tp": 1.870892,
+      "gross_pnl": 22.653457,
+      "entry_fee": 1.894608,
+      "exit_fee": 1.90367,
+      "net_pnl": 18.855179,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 64.9515011671277,
+        "macd_hist": 8.017825296896758e-05,
+        "atr": 0.004452680396625609,
+        "adx": 29.061543249865803
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2026-01-02 14:30:00",
+      "exit_time": "2026-01-02 14:45:00",
+      "entry_price": 1.906991,
+      "exit_price": 1.92129,
+      "quantity": 2458.8,
+      "sl": 1.892691,
+      "tp": 1.92129,
+      "gross_pnl": 35.159553,
+      "entry_fee": 1.875563,
+      "exit_fee": 1.889627,
+      "net_pnl": 31.394362,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 68.243618769103,
+        "macd_hist": 0.00021763021087121363,
+        "atr": 0.007149738287103824,
+        "adx": 34.75978288472445
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2026-01-04 00:45:00",
+      "exit_time": "2026-01-04 01:30:00",
+      "entry_price": 2.041396,
+      "exit_price": 2.026932,
+      "quantity": 2251.8,
+      "sl": 2.05586,
+      "tp": 2.026932,
+      "gross_pnl": 32.569888,
+      "entry_fee": 1.838726,
+      "exit_fee": 1.825698,
+      "net_pnl": 28.905464,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 78.42031027026397,
+        "macd_hist": 0.002773445174521872,
+        "atr": 0.007231967338050755,
+        "adx": 25.06146716762975
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2026-01-04 03:00:00",
+      "exit_time": "2026-01-04 03:45:00",
+      "entry_price": 2.038904,
+      "exit_price": 2.053633,
+      "quantity": 2209.5,
+      "sl": 2.024175,
+      "tp": 2.053633,
+      "gross_pnl": 32.54375,
+      "entry_fee": 1.801983,
+      "exit_fee": 1.815001,
+      "net_pnl": 28.926766,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 66.00101725582081,
+        "macd_hist": 4.503977849404806e-05,
+        "atr": 0.007364505506906315,
+        "adx": 30.991168735172053
+      },
+      "fold": 3
+    }
+  ],
+  "validation": {
+    "overall": "FAIL",
+    "checks": [
+      {
+        "name": "exit_after_entry",
+        "passed": true,
+        "level": "FAIL",
+        "message": "모든 트레이드에서 청산 > 진입"
+      },
+      {
+        "name": "sl_tp_direction",
+        "passed": true,
+        "level": "FAIL",
+        "message": "SL/TP 방향 정합"
+      },
+      {
+        "name": "no_overlap",
+        "passed": true,
+        "level": "FAIL",
+        "message": "포지션 비중첩 확인"
+      },
+      {
+        "name": "positive_fees",
+        "passed": true,
+        "level": "FAIL",
+        "message": "수수료 양수 확인"
+      },
+      {
+        "name": "no_negative_balance",
+        "passed": true,
+        "level": "FAIL",
+        "message": "잔고 양수 유지"
+      },
+      {
+        "name": "win_rate_high",
+        "passed": true,
+        "level": "WARNING",
+        "message": "승률 정상 (66.7%)"
+      },
+      {
+        "name": "win_rate_low",
+        "passed": true,
+        "level": "WARNING",
+        "message": "승률 정상 (66.7%)"
+      },
+      {
+        "name": "mdd_nonzero",
+        "passed": true,
+        "level": "WARNING",
+        "message": "MDD 정상 (12.0%)"
+      },
+      {
+        "name": "trade_frequency",
+        "passed": false,
+        "level": "WARNING",
+        "message": "월 평균 4.0건 < 5건 — 신호 생성 부족"
+      },
+      {
+        "name": "profit_factor_high",
+        "passed": true,
+        "level": "WARNING",
+        "message": "PF 정상 (1.57)"
+      }
+    ]
+  }
+}
--- a/results/xrpusdt/wf_backtest_20260321_194417.json
+++ b/results/xrpusdt/wf_backtest_20260321_194417.json
@@ -0,0 +1,214 @@
+{
+  "mode": "walk_forward",
+  "config": {
+    "symbols": [
+      "XRPUSDT"
+    ],
+    "start": null,
+    "end": null,
+    "initial_balance": 1000.0,
+    "leverage": 10,
+    "fee_pct": 0.04,
+    "slippage_pct": 0.01,
+    "use_ml": true,
+    "ml_threshold": 0.55,
+    "max_daily_loss_pct": 0.05,
+    "max_positions": 3,
+    "max_same_direction": 2,
+    "margin_max_ratio": 0.5,
+    "margin_min_ratio": 0.2,
+    "margin_decay_rate": 0.0006,
+    "atr_sl_mult": 1.5,
+    "atr_tp_mult": 3.0,
+    "min_notional": 5.0,
+    "signal_threshold": 3,
+    "adx_threshold": 0,
+    "volume_multiplier": 1.5,
+    "train_months": 6,
+    "test_months": 1,
+    "time_weight_decay": 2.0,
+    "negative_ratio": 3
+  },
+  "summary": {
+    "total_trades": 3,
+    "total_pnl": -5.1514,
+    "return_pct": -0.52,
+    "win_rate": 33.33,
+    "avg_win": 66.3376,
+    "avg_loss": -35.7445,
+    "payoff_ratio": 1.86,
+    "max_consecutive_losses": 2,
+    "profit_factor": 0.93,
+    "max_drawdown_pct": 3.76,
+    "sharpe_ratio": -6.68,
+    "total_fees": 11.5694,
+    "close_reasons": {
+      "STOP_LOSS": 2,
+      "TAKE_PROFIT": 1
+    }
+  },
+  "folds": [
+    {
+      "fold": 1,
+      "train_period": "2025-03-05 ~ 2025-09-05",
+      "test_period": "2025-09-05 ~ 2025-10-05",
+      "summary": {
+        "total_trades": 3,
+        "total_pnl": -5.1514,
+        "return_pct": -0.52,
+        "win_rate": 33.33,
+        "avg_win": 66.3376,
+        "avg_loss": -35.7445,
+        "payoff_ratio": 1.86,
+        "max_consecutive_losses": 2,
+        "profit_factor": 0.93,
+        "max_drawdown_pct": 3.76,
+        "sharpe_ratio": -6.68,
+        "total_fees": 11.5694,
+        "close_reasons": {
+          "STOP_LOSS": 2,
+          "TAKE_PROFIT": 1
+        }
+      }
+    }
+  ],
+  "trades": [
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-24 03:15:00",
+      "exit_time": "2025-09-24 04:30:00",
+      "entry_price": 2.811019,
+      "exit_price": 2.828555,
+      "quantity": 1778.5,
+      "sl": 2.828555,
+      "tp": 2.775947,
+      "gross_pnl": -31.18734,
+      "entry_fee": 1.999759,
+      "exit_fee": 2.012234,
+      "net_pnl": -35.199332,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": 0.5782,
+      "indicators": {
+        "rsi": 35.41445012242145,
+        "macd_hist": -0.0005539721484064007,
+        "atr": 0.011690503070987813,
+        "adx": 22.830095368917625
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-25 12:15:00",
+      "exit_time": "2025-09-25 12:30:00",
+      "entry_price": 2.793221,
+      "exit_price": 2.811993,
+      "quantity": 1726.9,
+      "sl": 2.811993,
+      "tp": 2.755676,
+      "gross_pnl": -32.41776,
+      "entry_fee": 1.929445,
+      "exit_fee": 1.942412,
+      "net_pnl": -36.289617,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": 0.724,
+      "indicators": {
+        "rsi": 27.256149561284357,
+        "macd_hist": -0.0005773233003328118,
+        "atr": 0.012514818420656685,
+        "adx": 36.706433983392714
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-26 09:30:00",
+      "exit_time": "2025-09-26 11:00:00",
+      "entry_price": 2.742026,
+      "exit_price": 2.700663,
+      "quantity": 1692.9,
+      "sl": 2.762707,
+      "tp": 2.700663,
+      "gross_pnl": 70.023157,
+      "entry_fee": 1.85679,
+      "exit_fee": 1.828781,
+      "net_pnl": 66.337586,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": 0.8238,
+      "indicators": {
+        "rsi": 42.61073221775071,
+        "macd_hist": -0.0004772649982219266,
+        "atr": 0.013787614360953772,
+        "adx": 15.435644479956943
+      },
+      "fold": 1
+    }
+  ],
+  "validation": {
+    "overall": "FAIL",
+    "checks": [
+      {
+        "name": "exit_after_entry",
+        "passed": true,
+        "level": "FAIL",
+        "message": "모든 트레이드에서 청산 > 진입"
+      },
+      {
+        "name": "sl_tp_direction",
+        "passed": true,
+        "level": "FAIL",
+        "message": "SL/TP 방향 정합"
+      },
+      {
+        "name": "no_overlap",
+        "passed": true,
+        "level": "FAIL",
+        "message": "포지션 비중첩 확인"
+      },
+      {
+        "name": "positive_fees",
+        "passed": true,
+        "level": "FAIL",
+        "message": "수수료 양수 확인"
+      },
+      {
+        "name": "no_negative_balance",
+        "passed": true,
+        "level": "FAIL",
+        "message": "잔고 양수 유지"
+      },
+      {
+        "name": "win_rate_high",
+        "passed": true,
+        "level": "WARNING",
+        "message": "승률 정상 (33.3%)"
+      },
+      {
+        "name": "win_rate_low",
+        "passed": true,
+        "level": "WARNING",
+        "message": "승률 정상 (33.3%)"
+      },
+      {
+        "name": "mdd_nonzero",
+        "passed": true,
+        "level": "WARNING",
+        "message": "MDD 정상 (3.8%)"
+      },
+      {
+        "name": "trade_frequency",
+        "passed": false,
+        "level": "WARNING",
+        "message": "월 평균 3.0건 < 5건 — 신호 생성 부족"
+      },
+      {
+        "name": "profit_factor_high",
+        "passed": true,
+        "level": "WARNING",
+        "message": "PF 정상 (0.93)"
+      }
+    ]
+  }
+}
--- a/results/xrpusdt/wf_backtest_20260322_224634.json
+++ b/results/xrpusdt/wf_backtest_20260322_224634.json
@@ -0,0 +1,382 @@
+{
+  "mode": "walk_forward",
+  "config": {
+    "symbols": [
+      "XRPUSDT"
+    ],
+    "start": null,
+    "end": null,
+    "initial_balance": 1000.0,
+    "leverage": 20,
+    "fee_pct": 0.04,
+    "slippage_pct": 0.01,
+    "use_ml": false,
+    "ml_threshold": 0.55,
+    "max_daily_loss_pct": 0.05,
+    "max_positions": 3,
+    "max_same_direction": 2,
+    "margin_max_ratio": 0.5,
+    "margin_min_ratio": 0.2,
+    "margin_decay_rate": 0.0006,
+    "atr_sl_mult": 1.5,
+    "atr_tp_mult": 4.0,
+    "min_notional": 5.0,
+    "signal_threshold": 3,
+    "adx_threshold": 25.0,
+    "volume_multiplier": 2.5,
+    "train_months": 6,
+    "test_months": 1,
+    "time_weight_decay": 2.0,
+    "negative_ratio": 3
+  },
+  "summary": {
+    "total_trades": 10,
+    "total_pnl": -71.4118,
+    "return_pct": -7.14,
+    "win_rate": 30.0,
+    "avg_win": 116.5629,
+    "avg_loss": -60.1572,
+    "payoff_ratio": 1.94,
+    "max_consecutive_losses": 4,
+    "profit_factor": 0.83,
+    "max_drawdown_pct": 28.16,
+    "sharpe_ratio": -15.9,
+    "total_fees": 75.9924,
+    "close_reasons": {
+      "TAKE_PROFIT": 3,
+      "STOP_LOSS": 7
+    }
+  },
+  "folds": [
+    {
+      "fold": 1,
+      "train_period": "2025-03-05 ~ 2025-09-05",
+      "test_period": "2025-09-05 ~ 2025-10-05",
+      "summary": {
+        "total_trades": 10,
+        "total_pnl": -71.4118,
+        "return_pct": -7.14,
+        "win_rate": 30.0,
+        "avg_win": 116.5629,
+        "avg_loss": -60.1572,
+        "payoff_ratio": 1.94,
+        "max_consecutive_losses": 4,
+        "profit_factor": 0.83,
+        "max_drawdown_pct": 28.16,
+        "sharpe_ratio": -15.9,
+        "total_fees": 75.9924,
+        "close_reasons": {
+          "TAKE_PROFIT": 3,
+          "STOP_LOSS": 7
+        }
+      }
+    }
+  ],
+  "trades": [
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-05 19:45:00",
+      "exit_time": "2025-09-05 22:15:00",
+      "entry_price": 2.863514,
+      "exit_price": 2.815423,
+      "quantity": 3491.9,
+      "sl": 2.881548,
+      "tp": 2.815423,
+      "gross_pnl": 167.927076,
+      "entry_fee": 3.999641,
+      "exit_fee": 3.93247,
+      "net_pnl": 159.994965,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 66.8667614741176,
+        "macd_hist": 0.005566660638547516,
+        "atr": 0.012022614930199287,
+        "adx": 25.794325095274626
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-07 07:30:00",
+      "exit_time": "2025-09-07 10:15:00",
+      "entry_price": 2.831483,
+      "exit_price": 2.825709,
+      "quantity": 3310.6,
+      "sl": 2.825709,
+      "tp": 2.846882,
+      "gross_pnl": -19.117005,
+      "entry_fee": 3.749563,
+      "exit_fee": 3.741916,
+      "net_pnl": -26.608485,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 70.72939012092385,
+        "macd_hist": 0.00013947818915852105,
+        "atr": 0.0038496557346203194,
+        "adx": 25.87514662158794
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-07 14:15:00",
+      "exit_time": "2025-09-07 14:30:00",
+      "entry_price": 2.888611,
+      "exit_price": 2.907326,
+      "quantity": 3295.3,
+      "sl": 2.907326,
+      "tp": 2.838705,
+      "gross_pnl": -61.671288,
+      "entry_fee": 3.807536,
+      "exit_fee": 3.832205,
+      "net_pnl": -69.311028,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 76.27147788789821,
+        "macd_hist": 0.006331113894477991,
+        "atr": 0.012476615713124774,
+        "adx": 29.135371839765913
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-09 07:00:00",
+      "exit_time": "2025-09-09 07:15:00",
+      "entry_price": 3.009099,
+      "exit_price": 3.026836,
+      "quantity": 3264.0,
+      "sl": 3.026836,
+      "tp": 2.9618,
+      "gross_pnl": -57.893469,
+      "entry_fee": 3.92868,
+      "exit_fee": 3.951837,
+      "net_pnl": -65.773986,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 73.38194905544675,
+        "macd_hist": 0.006160466326798137,
+        "atr": 0.011824646391069867,
+        "adx": 28.105801823891394
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-12 20:45:00",
+      "exit_time": "2025-09-13 08:45:00",
+      "entry_price": 3.121788,
+      "exit_price": 3.143446,
+      "quantity": 3197.5,
+      "sl": 3.143446,
+      "tp": 3.064033,
+      "gross_pnl": -69.251372,
+      "entry_fee": 3.992767,
+      "exit_fee": 4.020467,
+      "net_pnl": -77.264606,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 78.88995114530964,
+        "macd_hist": 0.004793783646225545,
+        "atr": 0.014438649390670705,
+        "adx": 33.848649235778474
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-14 11:15:00",
+      "exit_time": "2025-09-14 13:45:00",
+      "entry_price": 3.066993,
+      "exit_price": 3.033085,
+      "quantity": 3002.8,
+      "sl": 3.079709,
+      "tp": 3.033085,
+      "gross_pnl": 101.818765,
+      "entry_fee": 3.683827,
+      "exit_fee": 3.643099,
+      "net_pnl": 94.491838,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 31.419480021379645,
+        "macd_hist": -0.0003629091436070245,
+        "atr": 0.008476985221720718,
+        "adx": 31.882046477112183
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-20 14:00:00",
+      "exit_time": "2025-09-20 14:45:00",
+      "entry_price": 2.971603,
+      "exit_price": 2.980986,
+      "quantity": 3353.4,
+      "sl": 2.980986,
+      "tp": 2.94658,
+      "gross_pnl": -31.466181,
+      "entry_fee": 3.985989,
+      "exit_fee": 3.998576,
+      "net_pnl": -39.450746,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 36.09553473183674,
+        "macd_hist": -0.00018720159437711752,
+        "atr": 0.006255577606168083,
+        "adx": 28.84076206692945
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-24 19:45:00",
+      "exit_time": "2025-09-24 20:30:00",
+      "entry_price": 2.976198,
+      "exit_price": 2.955734,
+      "quantity": 3279.9,
+      "sl": 2.955734,
+      "tp": 3.030766,
+      "gross_pnl": -67.117005,
+      "entry_fee": 3.904652,
+      "exit_fee": 3.877805,
+      "net_pnl": -74.899463,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 77.25608496751632,
+        "macd_hist": 0.00019635721897620986,
+        "atr": 0.013642083686890932,
+        "adx": 66.36435142210216
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-25 12:15:00",
+      "exit_time": "2025-09-25 12:30:00",
+      "entry_price": 2.793221,
+      "exit_price": 2.811993,
+      "quantity": 3226.0,
+      "sl": 2.811993,
+      "tp": 2.743161,
+      "gross_pnl": -60.559206,
+      "entry_fee": 3.604372,
+      "exit_fee": 3.628596,
+      "net_pnl": -67.792174,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 27.256149561284357,
+        "macd_hist": -0.0005773233003328118,
+        "atr": 0.012514818420656685,
+        "adx": 36.706433983392714
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-28 22:00:00",
+      "exit_time": "2025-09-29 07:15:00",
+      "entry_price": 2.850785,
+      "exit_price": 2.885643,
+      "quantity": 2923.6,
+      "sl": 2.837713,
+      "tp": 2.885643,
+      "gross_pnl": 101.910302,
+      "entry_fee": 3.333822,
+      "exit_fee": 3.374586,
+      "net_pnl": 95.201894,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 69.94607598871028,
+        "macd_hist": 0.0002172037763433672,
+        "atr": 0.008714453238038499,
+        "adx": 45.96715774504039
+      },
+      "fold": 1
+    }
+  ],
+  "validation": {
+    "overall": "PASS",
+    "checks": [
+      {
+        "name": "exit_after_entry",
+        "passed": true,
+        "level": "FAIL",
+        "message": "모든 트레이드에서 청산 > 진입"
+      },
+      {
+        "name": "sl_tp_direction",
+        "passed": true,
+        "level": "FAIL",
+        "message": "SL/TP 방향 정합"
+      },
+      {
+        "name": "no_overlap",
+        "passed": true,
+        "level": "FAIL",
+        "message": "포지션 비중첩 확인"
+      },
+      {
+        "name": "positive_fees",
+        "passed": true,
+        "level": "FAIL",
+        "message": "수수료 양수 확인"
+      },
+      {
+        "name": "no_negative_balance",
+        "passed": true,
+        "level": "FAIL",
+        "message": "잔고 양수 유지"
+      },
+      {
+        "name": "win_rate_high",
+        "passed": true,
+        "level": "WARNING",
+        "message": "승률 정상 (30.0%)"
+      },
+      {
+        "name": "win_rate_low",
+        "passed": true,
+        "level": "WARNING",
+        "message": "승률 정상 (30.0%)"
+      },
+      {
+        "name": "mdd_nonzero",
+        "passed": true,
+        "level": "WARNING",
+        "message": "MDD 정상 (28.2%)"
+      },
+      {
+        "name": "trade_frequency",
+        "passed": true,
+        "level": "WARNING",
+        "message": "월 평균 10.0건"
+      },
+      {
+        "name": "profit_factor_high",
+        "passed": true,
+        "level": "WARNING",
+        "message": "PF 정상 (0.83)"
+      }
+    ]
+  }
+}
--- a/results/xrpusdt/wf_backtest_20260322_224727.json
+++ b/results/xrpusdt/wf_backtest_20260322_224727.json
@@ -0,0 +1,838 @@
+{
+  "mode": "walk_forward",
+  "config": {
+    "symbols": [
+      "XRPUSDT"
+    ],
+    "start": null,
+    "end": null,
+    "initial_balance": 1000.0,
+    "leverage": 20,
+    "fee_pct": 0.04,
+    "slippage_pct": 0.01,
+    "use_ml": false,
+    "ml_threshold": 0.55,
+    "max_daily_loss_pct": 0.05,
+    "max_positions": 3,
+    "max_same_direction": 2,
+    "margin_max_ratio": 0.5,
+    "margin_min_ratio": 0.2,
+    "margin_decay_rate": 0.0006,
+    "atr_sl_mult": 1.5,
+    "atr_tp_mult": 4.0,
+    "min_notional": 5.0,
+    "signal_threshold": 3,
+    "adx_threshold": 25.0,
+    "volume_multiplier": 2.5,
+    "train_months": 3,
+    "test_months": 1,
+    "time_weight_decay": 2.0,
+    "negative_ratio": 3
+  },
+  "summary": {
+    "total_trades": 27,
+    "total_pnl": 817.0717,
+    "return_pct": 81.71,
+    "win_rate": 44.44,
+    "avg_win": 140.6556,
+    "avg_loss": -58.053,
+    "payoff_ratio": 2.42,
+    "max_consecutive_losses": 4,
+    "profit_factor": 1.94,
+    "max_drawdown_pct": 20.23,
+    "sharpe_ratio": 51.77,
+    "total_fees": 195.3719,
+    "close_reasons": {
+      "STOP_LOSS": 15,
+      "TAKE_PROFIT": 11,
+      "REVERSE_SIGNAL": 1
+    }
+  },
+  "folds": [
+    {
+      "fold": 1,
+      "train_period": "2025-03-05 ~ 2025-06-05",
+      "test_period": "2025-06-05 ~ 2025-07-05",
+      "summary": {
+        "total_trades": 9,
+        "total_pnl": 454.4106,
+        "return_pct": 45.44,
+        "win_rate": 44.44,
+        "avg_win": 186.0558,
+        "avg_loss": -57.9625,
+        "payoff_ratio": 3.21,
+        "max_consecutive_losses": 2,
+        "profit_factor": 2.57,
+        "max_drawdown_pct": 8.26,
+        "sharpe_ratio": 73.09,
+        "total_fees": 60.8765,
+        "close_reasons": {
+          "STOP_LOSS": 5,
+          "TAKE_PROFIT": 4
+        }
+      }
+    },
+    {
+      "fold": 2,
+      "train_period": "2025-06-05 ~ 2025-09-05",
+      "test_period": "2025-09-05 ~ 2025-10-05",
+      "summary": {
+        "total_trades": 10,
+        "total_pnl": -71.4118,
+        "return_pct": -7.14,
+        "win_rate": 30.0,
+        "avg_win": 116.5629,
+        "avg_loss": -60.1572,
+        "payoff_ratio": 1.94,
+        "max_consecutive_losses": 4,
+        "profit_factor": 0.83,
+        "max_drawdown_pct": 28.16,
+        "sharpe_ratio": -15.9,
+        "total_fees": 75.9924,
+        "close_reasons": {
+          "TAKE_PROFIT": 3,
+          "STOP_LOSS": 7
+        }
+      }
+    },
+    {
+      "fold": 3,
+      "train_period": "2025-09-05 ~ 2025-12-05",
+      "test_period": "2025-12-05 ~ 2026-01-05",
+      "summary": {
+        "total_trades": 8,
+        "total_pnl": 434.073,
+        "return_pct": 43.41,
+        "win_rate": 62.5,
+        "avg_win": 118.7911,
+        "avg_loss": -53.2941,
+        "payoff_ratio": 2.23,
+        "max_consecutive_losses": 1,
+        "profit_factor": 3.71,
+        "max_drawdown_pct": 5.44,
+        "sharpe_ratio": 101.65,
+        "total_fees": 58.503,
+        "close_reasons": {
+          "STOP_LOSS": 3,
+          "TAKE_PROFIT": 4,
+          "REVERSE_SIGNAL": 1
+        }
+      }
+    }
+  ],
+  "trades": [
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-06-12 11:15:00",
+      "exit_time": "2025-06-12 12:30:00",
+      "entry_price": 2.223978,
+      "exit_price": 2.23446,
+      "quantity": 4496.0,
+      "sl": 2.23446,
+      "tp": 2.196023,
+      "gross_pnl": -47.13086,
+      "entry_fee": 3.999601,
+      "exit_fee": 4.018454,
+      "net_pnl": -55.148915,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 26.97199737318929,
+        "macd_hist": -0.0007807103280135859,
+        "atr": 0.006988561711463904,
+        "adx": 43.4578914382015
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-06-13 00:00:00",
+      "exit_time": "2025-06-13 00:30:00",
+      "entry_price": 2.149685,
+      "exit_price": 2.095237,
+      "quantity": 4394.9,
+      "sl": 2.170103,
+      "tp": 2.095237,
+      "gross_pnl": 239.292043,
+      "entry_fee": 3.77906,
+      "exit_fee": 3.683343,
+      "net_pnl": 231.829639,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 26.809985061770455,
+        "macd_hist": -0.0014287229374708253,
+        "atr": 0.01361191626294587,
+        "adx": 45.994286262673526
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-06-16 22:30:00",
+      "exit_time": "2025-06-16 23:45:00",
+      "entry_price": 2.260826,
+      "exit_price": 2.23893,
+      "quantity": 4101.6,
+      "sl": 2.23893,
+      "tp": 2.319216,
+      "gross_pnl": -89.809678,
+      "entry_fee": 3.709202,
+      "exit_fee": 3.673278,
+      "net_pnl": -97.192157,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 33.211506920436555,
+        "macd_hist": -0.007666291215691772,
+        "atr": 0.014597503086660083,
+        "adx": 41.77057022158849
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-06-17 15:00:00",
+      "exit_time": "2025-06-17 17:00:00",
+      "entry_price": 2.188781,
+      "exit_price": 2.14109,
+      "quantity": 4461.0,
+      "sl": 2.206665,
+      "tp": 2.14109,
+      "gross_pnl": 212.751364,
+      "entry_fee": 3.905661,
+      "exit_fee": 3.82056,
+      "net_pnl": 205.025142,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 35.98442517376965,
+        "macd_hist": -0.000473160901783975,
+        "atr": 0.011922851577807921,
+        "adx": 31.230008994240638
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-06-21 13:30:00",
+      "exit_time": "2025-06-21 14:00:00",
+      "entry_price": 2.119112,
+      "exit_price": 2.112041,
+      "quantity": 3992.4,
+      "sl": 2.112041,
+      "tp": 2.137967,
+      "gross_pnl": -28.228437,
+      "entry_fee": 3.384137,
+      "exit_fee": 3.372846,
+      "net_pnl": -34.98542,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 29.460371663394117,
+        "macd_hist": -0.002291006577745399,
+        "atr": 0.0047136955379463,
+        "adx": 26.139853452702802
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-06-21 21:15:00",
+      "exit_time": "2025-06-21 21:30:00",
+      "entry_price": 2.045995,
+      "exit_price": 1.990773,
+      "quantity": 4278.1,
+      "sl": 2.066704,
+      "tp": 1.990773,
+      "gross_pnl": 236.248138,
+      "entry_fee": 3.501189,
+      "exit_fee": 3.40669,
+      "net_pnl": 229.340259,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 24.112041978961905,
+        "macd_hist": -0.0015821538372272313,
+        "atr": 0.013805669484335523,
+        "adx": 47.020225174544926
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-06-24 05:30:00",
+      "exit_time": "2025-06-24 08:00:00",
+      "entry_price": 2.184818,
+      "exit_price": 2.167742,
+      "quantity": 2879.5,
+      "sl": 2.167742,
+      "tp": 2.230355,
+      "gross_pnl": -49.171401,
+      "entry_fee": 2.516474,
+      "exit_fee": 2.496805,
+      "net_pnl": -54.18468,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 73.02163697288638,
+        "macd_hist": 0.0005479493365071683,
+        "atr": 0.011384245075129916,
+        "adx": 47.36536786932758
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-07-01 13:00:00",
+      "exit_time": "2025-07-01 14:00:00",
+      "entry_price": 2.185781,
+      "exit_price": 2.19914,
+      "quantity": 3196.0,
+      "sl": 2.19914,
+      "tp": 2.150157,
+      "gross_pnl": -42.695683,
+      "entry_fee": 2.794303,
+      "exit_fee": 2.811381,
+      "net_pnl": -48.301367,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 34.25494593254047,
+        "macd_hist": -0.00014675405719808375,
+        "atr": 0.008906066514248343,
+        "adx": 38.40722178323835
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-07-04 06:00:00",
+      "exit_time": "2025-07-04 08:15:00",
+      "entry_price": 2.232877,
+      "exit_price": 2.208013,
+      "quantity": 3379.7,
+      "sl": 2.242201,
+      "tp": 2.208013,
+      "gross_pnl": 84.031619,
+      "entry_fee": 3.018581,
+      "exit_fee": 2.984969,
+      "net_pnl": 78.028069,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 31.442919224174045,
+        "macd_hist": -0.00029321477558042104,
+        "atr": 0.0062159081353788895,
+        "adx": 33.56850119916028
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-05 19:45:00",
+      "exit_time": "2025-09-05 22:15:00",
+      "entry_price": 2.863514,
+      "exit_price": 2.815423,
+      "quantity": 3491.9,
+      "sl": 2.881548,
+      "tp": 2.815423,
+      "gross_pnl": 167.927076,
+      "entry_fee": 3.999641,
+      "exit_fee": 3.93247,
+      "net_pnl": 159.994965,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 66.8667614741176,
+        "macd_hist": 0.005566660638547516,
+        "atr": 0.012022614930199287,
+        "adx": 25.794325095274626
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-07 07:30:00",
+      "exit_time": "2025-09-07 10:15:00",
+      "entry_price": 2.831483,
+      "exit_price": 2.825709,
+      "quantity": 3310.6,
+      "sl": 2.825709,
+      "tp": 2.846882,
+      "gross_pnl": -19.117005,
+      "entry_fee": 3.749563,
+      "exit_fee": 3.741916,
+      "net_pnl": -26.608485,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 70.72939012092385,
+        "macd_hist": 0.00013947818915852105,
+        "atr": 0.0038496557346203194,
+        "adx": 25.87514662158794
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-07 14:15:00",
+      "exit_time": "2025-09-07 14:30:00",
+      "entry_price": 2.888611,
+      "exit_price": 2.907326,
+      "quantity": 3295.3,
+      "sl": 2.907326,
+      "tp": 2.838705,
+      "gross_pnl": -61.671288,
+      "entry_fee": 3.807536,
+      "exit_fee": 3.832205,
+      "net_pnl": -69.311028,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 76.27147788789821,
+        "macd_hist": 0.006331113894477991,
+        "atr": 0.012476615713124774,
+        "adx": 29.135371839765913
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-09 07:00:00",
+      "exit_time": "2025-09-09 07:15:00",
+      "entry_price": 3.009099,
+      "exit_price": 3.026836,
+      "quantity": 3264.0,
+      "sl": 3.026836,
+      "tp": 2.9618,
+      "gross_pnl": -57.893469,
+      "entry_fee": 3.92868,
+      "exit_fee": 3.951837,
+      "net_pnl": -65.773986,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 73.38194905544675,
+        "macd_hist": 0.006160466326798137,
+        "atr": 0.011824646391069867,
+        "adx": 28.105801823891394
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-12 20:45:00",
+      "exit_time": "2025-09-13 08:45:00",
+      "entry_price": 3.121788,
+      "exit_price": 3.143446,
+      "quantity": 3197.5,
+      "sl": 3.143446,
+      "tp": 3.064033,
+      "gross_pnl": -69.251372,
+      "entry_fee": 3.992767,
+      "exit_fee": 4.020467,
+      "net_pnl": -77.264606,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 78.88995114530964,
+        "macd_hist": 0.004793783646225545,
+        "atr": 0.014438649390670705,
+        "adx": 33.848649235778474
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-14 11:15:00",
+      "exit_time": "2025-09-14 13:45:00",
+      "entry_price": 3.066993,
+      "exit_price": 3.033085,
+      "quantity": 3002.8,
+      "sl": 3.079709,
+      "tp": 3.033085,
+      "gross_pnl": 101.818765,
+      "entry_fee": 3.683827,
+      "exit_fee": 3.643099,
+      "net_pnl": 94.491838,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 31.419480021379645,
+        "macd_hist": -0.0003629091436070245,
+        "atr": 0.008476985221720718,
+        "adx": 31.882046477112183
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-20 14:00:00",
+      "exit_time": "2025-09-20 14:45:00",
+      "entry_price": 2.971603,
+      "exit_price": 2.980986,
+      "quantity": 3353.4,
+      "sl": 2.980986,
+      "tp": 2.94658,
+      "gross_pnl": -31.466181,
+      "entry_fee": 3.985989,
+      "exit_fee": 3.998576,
+      "net_pnl": -39.450746,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 36.09553473183674,
+        "macd_hist": -0.00018720159437711752,
+        "atr": 0.006255577606168083,
+        "adx": 28.84076206692945
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-24 19:45:00",
+      "exit_time": "2025-09-24 20:30:00",
+      "entry_price": 2.976198,
+      "exit_price": 2.955734,
+      "quantity": 3279.9,
+      "sl": 2.955734,
+      "tp": 3.030766,
+      "gross_pnl": -67.117005,
+      "entry_fee": 3.904652,
+      "exit_fee": 3.877805,
+      "net_pnl": -74.899463,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 77.25608496751632,
+        "macd_hist": 0.00019635721897620986,
+        "atr": 0.013642083686890932,
+        "adx": 66.36435142210216
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-25 12:15:00",
+      "exit_time": "2025-09-25 12:30:00",
+      "entry_price": 2.793221,
+      "exit_price": 2.811993,
+      "quantity": 3226.0,
+      "sl": 2.811993,
+      "tp": 2.743161,
+      "gross_pnl": -60.559206,
+      "entry_fee": 3.604372,
+      "exit_fee": 3.628596,
+      "net_pnl": -67.792174,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 27.256149561284357,
+        "macd_hist": -0.0005773233003328118,
+        "atr": 0.012514818420656685,
+        "adx": 36.706433983392714
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-28 22:00:00",
+      "exit_time": "2025-09-29 07:15:00",
+      "entry_price": 2.850785,
+      "exit_price": 2.885643,
+      "quantity": 2923.6,
+      "sl": 2.837713,
+      "tp": 2.885643,
+      "gross_pnl": 101.910302,
+      "entry_fee": 3.333822,
+      "exit_fee": 3.374586,
+      "net_pnl": 95.201894,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 69.94607598871028,
+        "macd_hist": 0.0002172037763433672,
+        "atr": 0.008714453238038499,
+        "adx": 45.96715774504039
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-12-10 10:30:00",
+      "exit_time": "2025-12-10 18:30:00",
+      "entry_price": 2.069993,
+      "exit_price": 2.080244,
+      "quantity": 4830.5,
+      "sl": 2.080244,
+      "tp": 2.042658,
+      "gross_pnl": -49.515419,
+      "entry_fee": 3.99964,
+      "exit_fee": 4.019447,
+      "net_pnl": -57.534506,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 37.038012691554805,
+        "macd_hist": -9.211636302669133e-05,
+        "atr": 0.0068337189344636114,
+        "adx": 28.943927763667713
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-12-12 16:00:00",
+      "exit_time": "2025-12-13 05:00:00",
+      "entry_price": 1.988899,
+      "exit_price": 2.037103,
+      "quantity": 4739.1,
+      "sl": 1.970822,
+      "tp": 2.037103,
+      "gross_pnl": 228.445099,
+      "entry_fee": 3.770236,
+      "exit_fee": 3.861614,
+      "net_pnl": 220.813249,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 28.182013495720106,
+        "macd_hist": -0.00643391832048344,
+        "atr": 0.01205108033747697,
+        "adx": 30.769786891839054
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-12-19 13:15:00",
+      "exit_time": "2025-12-19 15:15:00",
+      "entry_price": 1.878712,
+      "exit_price": 1.889911,
+      "quantity": 4978.2,
+      "sl": 1.889911,
+      "tp": 1.84885,
+      "gross_pnl": -55.748245,
+      "entry_fee": 3.741042,
+      "exit_fee": 3.763341,
+      "net_pnl": -63.252628,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 68.16547032772114,
+        "macd_hist": -4.5929936914913816e-05,
+        "atr": 0.007465649526915487,
+        "adx": 40.69667585881617
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-12-25 23:30:00",
+      "exit_time": "2025-12-26 02:15:00",
+      "entry_price": 1.831783,
+      "exit_price": 1.857641,
+      "quantity": 5284.9,
+      "sl": 1.822086,
+      "tp": 1.857641,
+      "gross_pnl": 136.657597,
+      "entry_fee": 3.872316,
+      "exit_fee": 3.926979,
+      "net_pnl": 128.858301,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 18.688435627302994,
+        "macd_hist": -0.0034657628634239823,
+        "atr": 0.006464530874639477,
+        "adx": 30.228290924248867
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2026-01-01 15:45:00",
+      "exit_time": "2026-01-01 16:15:00",
+      "entry_price": 1.861986,
+      "exit_price": 1.855307,
+      "quantity": 4787.6,
+      "sl": 1.855307,
+      "tp": 1.879797,
+      "gross_pnl": -31.976479,
+      "entry_fee": 3.565778,
+      "exit_fee": 3.552987,
+      "net_pnl": -39.095244,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 64.9515011671277,
+        "macd_hist": 8.017825296896758e-05,
+        "atr": 0.004452680396625609,
+        "adx": 29.061543249865803
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2026-01-02 14:30:00",
+      "exit_time": "2026-01-02 16:15:00",
+      "entry_price": 1.906991,
+      "exit_price": 1.93559,
+      "quantity": 4818.6,
+      "sl": 1.896266,
+      "tp": 1.93559,
+      "gross_pnl": 137.806916,
+      "entry_fee": 3.67561,
+      "exit_fee": 3.730733,
+      "net_pnl": 130.400573,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 68.243618769103,
+        "macd_hist": 0.00021763021087121363,
+        "atr": 0.007149738287103824,
+        "adx": 34.75978288472445
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2026-01-04 00:45:00",
+      "exit_time": "2026-01-04 03:00:00",
+      "entry_price": 2.041396,
+      "exit_price": 2.038904,
+      "quantity": 3981.9,
+      "sl": 2.052244,
+      "tp": 2.012468,
+      "gross_pnl": 9.922775,
+      "entry_fee": 3.251454,
+      "exit_fee": 3.247485,
+      "net_pnl": 3.423837,
+      "close_reason": "REVERSE_SIGNAL",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 78.42031027026397,
+        "macd_hist": 0.002773445174521872,
+        "atr": 0.007231967338050755,
+        "adx": 25.06146716762975
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2026-01-04 03:00:00",
+      "exit_time": "2026-01-04 05:15:00",
+      "entry_price": 2.038904,
+      "exit_price": 2.068362,
+      "quantity": 3971.2,
+      "sl": 2.027857,
+      "tp": 2.068362,
+      "gross_pnl": 116.983697,
+      "entry_fee": 3.238758,
+      "exit_fee": 3.285551,
+      "net_pnl": 110.459388,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 66.00101725582081,
+        "macd_hist": 4.503977849404806e-05,
+        "atr": 0.007364505506906315,
+        "adx": 30.991168735172053
+      },
+      "fold": 3
+    }
+  ],
+  "validation": {
+    "overall": "FAIL",
+    "checks": [
+      {
+        "name": "exit_after_entry",
+        "passed": true,
+        "level": "FAIL",
+        "message": "모든 트레이드에서 청산 > 진입"
+      },
+      {
+        "name": "sl_tp_direction",
+        "passed": true,
+        "level": "FAIL",
+        "message": "SL/TP 방향 정합"
+      },
+      {
+        "name": "no_overlap",
+        "passed": true,
+        "level": "FAIL",
+        "message": "포지션 비중첩 확인"
+      },
+      {
+        "name": "positive_fees",
+        "passed": true,
+        "level": "FAIL",
+        "message": "수수료 양수 확인"
+      },
+      {
+        "name": "no_negative_balance",
+        "passed": true,
+        "level": "FAIL",
+        "message": "잔고 양수 유지"
+      },
+      {
+        "name": "win_rate_high",
+        "passed": true,
+        "level": "WARNING",
+        "message": "승률 정상 (44.4%)"
+      },
+      {
+        "name": "win_rate_low",
+        "passed": true,
+        "level": "WARNING",
+        "message": "승률 정상 (44.4%)"
+      },
+      {
+        "name": "mdd_nonzero",
+        "passed": true,
+        "level": "WARNING",
+        "message": "MDD 정상 (20.2%)"
+      },
+      {
+        "name": "trade_frequency",
+        "passed": false,
+        "level": "WARNING",
+        "message": "월 평균 4.0건 < 5건 — 신호 생성 부족"
+      },
+      {
+        "name": "profit_factor_high",
+        "passed": true,
+        "level": "WARNING",
+        "message": "PF 정상 (1.94)"
+      }
+    ]
+  }
+}
--- a/results/xrpusdt/wf_backtest_20260322_231113.json
+++ b/results/xrpusdt/wf_backtest_20260322_231113.json
@@ -0,0 +1,511 @@
+{
+  "mode": "walk_forward",
+  "config": {
+    "symbols": [
+      "XRPUSDT"
+    ],
+    "start": null,
+    "end": null,
+    "initial_balance": 1000.0,
+    "leverage": 10,
+    "fee_pct": 0.04,
+    "slippage_pct": 0.01,
+    "use_ml": false,
+    "ml_threshold": 0.55,
+    "max_daily_loss_pct": 0.05,
+    "max_positions": 3,
+    "max_same_direction": 2,
+    "margin_max_ratio": 0.5,
+    "margin_min_ratio": 0.2,
+    "margin_decay_rate": 0.0006,
+    "atr_sl_mult": 1.5,
+    "atr_tp_mult": 3.0,
+    "min_notional": 5.0,
+    "signal_threshold": 3,
+    "adx_threshold": 0,
+    "volume_multiplier": 1.5,
+    "train_months": 6,
+    "test_months": 1,
+    "time_weight_decay": 2.0,
+    "negative_ratio": 3
+  },
+  "summary": {
+    "total_trades": 15,
+    "total_pnl": -128.8207,
+    "return_pct": -12.88,
+    "win_rate": 26.67,
+    "avg_win": 38.6226,
+    "avg_loss": -25.7556,
+    "payoff_ratio": 1.5,
+    "max_consecutive_losses": 6,
+    "profit_factor": 0.55,
+    "max_drawdown_pct": 20.39,
+    "sharpe_ratio": -52.86,
+    "total_fees": 57.6972,
+    "close_reasons": {
+      "TAKE_PROFIT": 4,
+      "STOP_LOSS": 11
+    }
+  },
+  "folds": [
+    {
+      "fold": 1,
+      "train_period": "2025-03-05 ~ 2025-09-05",
+      "test_period": "2025-09-05 ~ 2025-10-05",
+      "test_start": "2025-09-05T15:00:00",
+      "test_end": "2025-10-05T15:00:00",
+      "summary": {
+        "total_trades": 15,
+        "total_pnl": -128.8207,
+        "return_pct": -12.88,
+        "win_rate": 26.67,
+        "avg_win": 38.6226,
+        "avg_loss": -25.7556,
+        "payoff_ratio": 1.5,
+        "max_consecutive_losses": 6,
+        "profit_factor": 0.55,
+        "max_drawdown_pct": 20.39,
+        "sharpe_ratio": -52.86,
+        "total_fees": 57.6972,
+        "close_reasons": {
+          "TAKE_PROFIT": 4,
+          "STOP_LOSS": 11
+        }
+      },
+      "market_context": {
+        "btc_return_pct": 11.2,
+        "eth_return_pct": 5.8,
+        "btc_avg_adx": 24.6,
+        "market_regime": "횡보",
+        "ls_ratio": null
+      }
+    }
+  ],
+  "trades": [
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-05 19:45:00",
+      "exit_time": "2025-09-05 21:15:00",
+      "entry_price": 2.863514,
+      "exit_price": 2.827446,
+      "quantity": 1745.9,
+      "sl": 2.881548,
+      "tp": 2.827446,
+      "gross_pnl": 62.97085,
+      "entry_fee": 1.999763,
+      "exit_fee": 1.974575,
+      "net_pnl": 58.996512,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 66.8667614741176,
+        "macd_hist": 0.005566660638547516,
+        "atr": 0.012022614930199287,
+        "adx": 25.794325095274626
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-06 09:00:00",
+      "exit_time": "2025-09-06 13:15:00",
+      "entry_price": 2.806619,
+      "exit_price": 2.812828,
+      "quantity": 1752.9,
+      "sl": 2.812828,
+      "tp": 2.794201,
+      "gross_pnl": -10.883731,
+      "entry_fee": 1.967889,
+      "exit_fee": 1.972243,
+      "net_pnl": -14.823863,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 34.00610631074574,
+        "macd_hist": -0.0004704685694576242,
+        "atr": 0.00413932368453192,
+        "adx": 14.008193990926515
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-06 15:45:00",
+      "exit_time": "2025-09-06 22:00:00",
+      "entry_price": 2.80062,
+      "exit_price": 2.807842,
+      "quantity": 1765.2,
+      "sl": 2.807842,
+      "tp": 2.786175,
+      "gross_pnl": -12.748682,
+      "entry_fee": 1.977462,
+      "exit_fee": 1.982561,
+      "net_pnl": -16.708704,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 38.58702631504332,
+        "macd_hist": -0.0004103175941632724,
+        "atr": 0.004814820425995649,
+        "adx": 15.495502216732291
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-07 07:30:00",
+      "exit_time": "2025-09-07 10:15:00",
+      "entry_price": 2.831483,
+      "exit_price": 2.825709,
+      "quantity": 1754.7,
+      "sl": 2.825709,
+      "tp": 2.843032,
+      "gross_pnl": -10.132486,
+      "entry_fee": 1.987361,
+      "exit_fee": 1.983308,
+      "net_pnl": -14.103156,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 70.72939012092385,
+        "macd_hist": 0.00013947818915852105,
+        "atr": 0.0038496557346203194,
+        "adx": 25.87514662158794
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-07 13:30:00",
+      "exit_time": "2025-09-07 14:00:00",
+      "entry_price": 2.840884,
+      "exit_price": 2.853506,
+      "quantity": 1755.1,
+      "sl": 2.834573,
+      "tp": 2.853506,
+      "gross_pnl": 22.153405,
+      "entry_fee": 1.994414,
+      "exit_fee": 2.003276,
+      "net_pnl": 18.155715,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 70.99242896973038,
+        "macd_hist": 0.0004291197510571344,
+        "atr": 0.0042074344637298,
+        "adx": 18.351295376801428
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-07 14:15:00",
+      "exit_time": "2025-09-07 14:30:00",
+      "entry_price": 2.888611,
+      "exit_price": 2.907326,
+      "quantity": 1717.8,
+      "sl": 2.907326,
+      "tp": 2.851181,
+      "gross_pnl": -32.148496,
+      "entry_fee": 1.984822,
+      "exit_fee": 1.997682,
+      "net_pnl": -36.131,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 76.27147788789821,
+        "macd_hist": 0.006331113894477991,
+        "atr": 0.012476615713124774,
+        "adx": 29.135371839765913
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-07 22:45:00",
+      "exit_time": "2025-09-08 02:15:00",
+      "entry_price": 2.875788,
+      "exit_price": 2.862379,
+      "quantity": 1730.8,
+      "sl": 2.862379,
+      "tp": 2.902605,
+      "gross_pnl": -23.207724,
+      "entry_fee": 1.990965,
+      "exit_fee": 1.981682,
+      "net_pnl": -27.180371,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 55.067227780514635,
+        "macd_hist": 0.00013194571339722526,
+        "atr": 0.008939112576366447,
+        "adx": 14.580517290441753
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-08 07:15:00",
+      "exit_time": "2025-09-08 09:45:00",
+      "entry_price": 2.90089,
+      "exit_price": 2.932746,
+      "quantity": 1669.0,
+      "sl": 2.884962,
+      "tp": 2.932746,
+      "gross_pnl": 53.167202,
+      "entry_fee": 1.936634,
+      "exit_fee": 1.957901,
+      "net_pnl": 49.272667,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 60.12434238530789,
+        "macd_hist": 0.00041228306459878275,
+        "atr": 0.010618574376478408,
+        "adx": 8.300763892347662
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-09 07:00:00",
+      "exit_time": "2025-09-09 07:15:00",
+      "entry_price": 3.009099,
+      "exit_price": 3.026836,
+      "quantity": 1655.0,
+      "sl": 3.026836,
+      "tp": 2.973625,
+      "gross_pnl": -29.354685,
+      "entry_fee": 1.992024,
+      "exit_fee": 2.003765,
+      "net_pnl": -33.350474,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 73.38194905544675,
+        "macd_hist": 0.006160466326798137,
+        "atr": 0.011824646391069867,
+        "adx": 28.105801823891394
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-09 23:00:00",
+      "exit_time": "2025-09-10 02:00:00",
+      "entry_price": 2.943406,
+      "exit_price": 2.956284,
+      "quantity": 1671.6,
+      "sl": 2.956284,
+      "tp": 2.917649,
+      "gross_pnl": -21.527774,
+      "entry_fee": 1.968079,
+      "exit_fee": 1.97669,
+      "net_pnl": -25.472542,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 39.53536171049937,
+        "macd_hist": -1.946210228058031e-05,
+        "atr": 0.008585695753008377,
+        "adx": 20.785784979630154
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-11 08:30:00",
+      "exit_time": "2025-09-11 11:15:00",
+      "entry_price": 3.017402,
+      "exit_price": 3.006355,
+      "quantity": 1588.7,
+      "sl": 3.006355,
+      "tp": 3.039494,
+      "gross_pnl": -17.549278,
+      "entry_fee": 1.917498,
+      "exit_fee": 1.910479,
+      "net_pnl": -21.377255,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 65.07990381213337,
+        "macd_hist": 0.0004440826925332865,
+        "atr": 0.007364208872183876,
+        "adx": 14.825623048829055
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-12 15:00:00",
+      "exit_time": "2025-09-12 16:15:00",
+      "entry_price": 3.019198,
+      "exit_price": 3.037941,
+      "quantity": 1552.0,
+      "sl": 3.037941,
+      "tp": 2.981711,
+      "gross_pnl": -29.089679,
+      "entry_fee": 1.874318,
+      "exit_fee": 1.885954,
+      "net_pnl": -32.849951,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 38.155616440178264,
+        "macd_hist": -0.0008867617207142038,
+        "atr": 0.012495566579322376,
+        "adx": 19.09633552921856
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-12 20:45:00",
+      "exit_time": "2025-09-13 08:45:00",
+      "entry_price": 3.121788,
+      "exit_price": 3.143446,
+      "quantity": 1448.4,
+      "sl": 3.143446,
+      "tp": 3.078472,
+      "gross_pnl": -31.36941,
+      "entry_fee": 1.808639,
+      "exit_fee": 1.821187,
+      "net_pnl": -34.999235,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 78.88995114530964,
+        "macd_hist": 0.004793783646225545,
+        "atr": 0.014438649390670705,
+        "adx": 33.848649235778474
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-13 09:15:00",
+      "exit_time": "2025-09-13 09:45:00",
+      "entry_price": 3.161284,
+      "exit_price": 3.177886,
+      "quantity": 1375.0,
+      "sl": 3.177886,
+      "tp": 3.128079,
+      "gross_pnl": -22.828175,
+      "entry_fee": 1.738706,
+      "exit_fee": 1.747837,
+      "net_pnl": -26.314718,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 75.37053214953528,
+        "macd_hist": 0.00511253369858191,
+        "atr": 0.011068206025146562,
+        "adx": 36.52494916026817
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-14 00:45:00",
+      "exit_time": "2025-09-14 01:15:00",
+      "entry_price": 3.109189,
+      "exit_price": 3.086009,
+      "quantity": 1355.7,
+      "sl": 3.120779,
+      "tp": 3.086009,
+      "gross_pnl": 31.425221,
+      "entry_fee": 1.686051,
+      "exit_fee": 1.673481,
+      "net_pnl": 28.065689,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 38.7433537799598,
+        "macd_hist": -0.0002412627790731375,
+        "atr": 0.007726689972056756,
+        "adx": 19.663365885823197
+      },
+      "fold": 1
+    }
+  ],
+  "validation": {
+    "overall": "PASS",
+    "checks": [
+      {
+        "name": "exit_after_entry",
+        "passed": true,
+        "level": "FAIL",
+        "message": "모든 트레이드에서 청산 > 진입"
+      },
+      {
+        "name": "sl_tp_direction",
+        "passed": true,
+        "level": "FAIL",
+        "message": "SL/TP 방향 정합"
+      },
+      {
+        "name": "no_overlap",
+        "passed": true,
+        "level": "FAIL",
+        "message": "포지션 비중첩 확인"
+      },
+      {
+        "name": "positive_fees",
+        "passed": true,
+        "level": "FAIL",
+        "message": "수수료 양수 확인"
+      },
+      {
+        "name": "no_negative_balance",
+        "passed": true,
+        "level": "FAIL",
+        "message": "잔고 양수 유지"
+      },
+      {
+        "name": "win_rate_high",
+        "passed": true,
+        "level": "WARNING",
+        "message": "승률 정상 (26.7%)"
+      },
+      {
+        "name": "win_rate_low",
+        "passed": true,
+        "level": "WARNING",
+        "message": "승률 정상 (26.7%)"
+      },
+      {
+        "name": "mdd_nonzero",
+        "passed": true,
+        "level": "WARNING",
+        "message": "MDD 정상 (20.4%)"
+      },
+      {
+        "name": "trade_frequency",
+        "passed": true,
+        "level": "WARNING",
+        "message": "월 평균 15.0건"
+      },
+      {
+        "name": "profit_factor_high",
+        "passed": true,
+        "level": "WARNING",
+        "message": "PF 정상 (0.55)"
+      }
+    ]
+  }
+}
--- a/results/xrpusdt/wf_backtest_20260322_231737.json
+++ b/results/xrpusdt/wf_backtest_20260322_231737.json
@@ -0,0 +1,865 @@
+{
+  "mode": "walk_forward",
+  "config": {
+    "symbols": [
+      "XRPUSDT"
+    ],
+    "start": null,
+    "end": null,
+    "initial_balance": 1000.0,
+    "leverage": 20,
+    "fee_pct": 0.04,
+    "slippage_pct": 0.01,
+    "use_ml": false,
+    "ml_threshold": 0.55,
+    "max_daily_loss_pct": 0.05,
+    "max_positions": 3,
+    "max_same_direction": 2,
+    "margin_max_ratio": 0.5,
+    "margin_min_ratio": 0.2,
+    "margin_decay_rate": 0.0006,
+    "atr_sl_mult": 1.5,
+    "atr_tp_mult": 4.0,
+    "min_notional": 5.0,
+    "signal_threshold": 3,
+    "adx_threshold": 25.0,
+    "volume_multiplier": 2.5,
+    "train_months": 3,
+    "test_months": 1,
+    "time_weight_decay": 2.0,
+    "negative_ratio": 3
+  },
+  "summary": {
+    "total_trades": 27,
+    "total_pnl": 817.0717,
+    "return_pct": 81.71,
+    "win_rate": 44.44,
+    "avg_win": 140.6556,
+    "avg_loss": -58.053,
+    "payoff_ratio": 2.42,
+    "max_consecutive_losses": 4,
+    "profit_factor": 1.94,
+    "max_drawdown_pct": 20.23,
+    "sharpe_ratio": 51.77,
+    "total_fees": 195.3719,
+    "close_reasons": {
+      "STOP_LOSS": 15,
+      "TAKE_PROFIT": 11,
+      "REVERSE_SIGNAL": 1
+    }
+  },
+  "folds": [
+    {
+      "fold": 1,
+      "train_period": "2025-03-05 ~ 2025-06-05",
+      "test_period": "2025-06-05 ~ 2025-07-05",
+      "test_start": "2025-06-05T15:00:00",
+      "test_end": "2025-07-05T15:00:00",
+      "summary": {
+        "total_trades": 9,
+        "total_pnl": 454.4106,
+        "return_pct": 45.44,
+        "win_rate": 44.44,
+        "avg_win": 186.0558,
+        "avg_loss": -57.9625,
+        "payoff_ratio": 3.21,
+        "max_consecutive_losses": 2,
+        "profit_factor": 2.57,
+        "max_drawdown_pct": 8.26,
+        "sharpe_ratio": 73.09,
+        "total_fees": 60.8765,
+        "close_reasons": {
+          "STOP_LOSS": 5,
+          "TAKE_PROFIT": 4
+        }
+      },
+      "market_context": {
+        "btc_return_pct": 3.7,
+        "eth_return_pct": -2.5,
+        "btc_avg_adx": 24.9,
+        "market_regime": "횡보",
+        "ls_ratio": null
+      }
+    },
+    {
+      "fold": 2,
+      "train_period": "2025-06-05 ~ 2025-09-05",
+      "test_period": "2025-09-05 ~ 2025-10-05",
+      "test_start": "2025-09-05T15:00:00",
+      "test_end": "2025-10-05T15:00:00",
+      "summary": {
+        "total_trades": 10,
+        "total_pnl": -71.4118,
+        "return_pct": -7.14,
+        "win_rate": 30.0,
+        "avg_win": 116.5629,
+        "avg_loss": -60.1572,
+        "payoff_ratio": 1.94,
+        "max_consecutive_losses": 4,
+        "profit_factor": 0.83,
+        "max_drawdown_pct": 28.16,
+        "sharpe_ratio": -15.9,
+        "total_fees": 75.9924,
+        "close_reasons": {
+          "TAKE_PROFIT": 3,
+          "STOP_LOSS": 7
+        }
+      },
+      "market_context": {
+        "btc_return_pct": 11.2,
+        "eth_return_pct": 5.8,
+        "btc_avg_adx": 24.6,
+        "market_regime": "횡보",
+        "ls_ratio": null
+      }
+    },
+    {
+      "fold": 3,
+      "train_period": "2025-09-05 ~ 2025-12-05",
+      "test_period": "2025-12-05 ~ 2026-01-05",
+      "test_start": "2025-12-05T15:00:00",
+      "test_end": "2026-01-05T15:00:00",
+      "summary": {
+        "total_trades": 8,
+        "total_pnl": 434.073,
+        "return_pct": 43.41,
+        "win_rate": 62.5,
+        "avg_win": 118.7911,
+        "avg_loss": -53.2941,
+        "payoff_ratio": 2.23,
+        "max_consecutive_losses": 1,
+        "profit_factor": 3.71,
+        "max_drawdown_pct": 5.44,
+        "sharpe_ratio": 101.65,
+        "total_fees": 58.503,
+        "close_reasons": {
+          "STOP_LOSS": 3,
+          "TAKE_PROFIT": 4,
+          "REVERSE_SIGNAL": 1
+        }
+      },
+      "market_context": {
+        "btc_return_pct": 2.6,
+        "eth_return_pct": 0.8,
+        "btc_avg_adx": 25.5,
+        "market_regime": "상승 추세",
+        "ls_ratio": null
+      }
+    }
+  ],
+  "trades": [
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-06-12 11:15:00",
+      "exit_time": "2025-06-12 12:30:00",
+      "entry_price": 2.223978,
+      "exit_price": 2.23446,
+      "quantity": 4496.0,
+      "sl": 2.23446,
+      "tp": 2.196023,
+      "gross_pnl": -47.13086,
+      "entry_fee": 3.999601,
+      "exit_fee": 4.018454,
+      "net_pnl": -55.148915,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 26.97199737318929,
+        "macd_hist": -0.0007807103280135859,
+        "atr": 0.006988561711463904,
+        "adx": 43.4578914382015
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-06-13 00:00:00",
+      "exit_time": "2025-06-13 00:30:00",
+      "entry_price": 2.149685,
+      "exit_price": 2.095237,
+      "quantity": 4394.9,
+      "sl": 2.170103,
+      "tp": 2.095237,
+      "gross_pnl": 239.292043,
+      "entry_fee": 3.77906,
+      "exit_fee": 3.683343,
+      "net_pnl": 231.829639,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 26.809985061770455,
+        "macd_hist": -0.0014287229374708253,
+        "atr": 0.01361191626294587,
+        "adx": 45.994286262673526
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-06-16 22:30:00",
+      "exit_time": "2025-06-16 23:45:00",
+      "entry_price": 2.260826,
+      "exit_price": 2.23893,
+      "quantity": 4101.6,
+      "sl": 2.23893,
+      "tp": 2.319216,
+      "gross_pnl": -89.809678,
+      "entry_fee": 3.709202,
+      "exit_fee": 3.673278,
+      "net_pnl": -97.192157,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 33.211506920436555,
+        "macd_hist": -0.007666291215691772,
+        "atr": 0.014597503086660083,
+        "adx": 41.77057022158849
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-06-17 15:00:00",
+      "exit_time": "2025-06-17 17:00:00",
+      "entry_price": 2.188781,
+      "exit_price": 2.14109,
+      "quantity": 4461.0,
+      "sl": 2.206665,
+      "tp": 2.14109,
+      "gross_pnl": 212.751364,
+      "entry_fee": 3.905661,
+      "exit_fee": 3.82056,
+      "net_pnl": 205.025142,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 35.98442517376965,
+        "macd_hist": -0.000473160901783975,
+        "atr": 0.011922851577807921,
+        "adx": 31.230008994240638
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-06-21 13:30:00",
+      "exit_time": "2025-06-21 14:00:00",
+      "entry_price": 2.119112,
+      "exit_price": 2.112041,
+      "quantity": 3992.4,
+      "sl": 2.112041,
+      "tp": 2.137967,
+      "gross_pnl": -28.228437,
+      "entry_fee": 3.384137,
+      "exit_fee": 3.372846,
+      "net_pnl": -34.98542,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 29.460371663394117,
+        "macd_hist": -0.002291006577745399,
+        "atr": 0.0047136955379463,
+        "adx": 26.139853452702802
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-06-21 21:15:00",
+      "exit_time": "2025-06-21 21:30:00",
+      "entry_price": 2.045995,
+      "exit_price": 1.990773,
+      "quantity": 4278.1,
+      "sl": 2.066704,
+      "tp": 1.990773,
+      "gross_pnl": 236.248138,
+      "entry_fee": 3.501189,
+      "exit_fee": 3.40669,
+      "net_pnl": 229.340259,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 24.112041978961905,
+        "macd_hist": -0.0015821538372272313,
+        "atr": 0.013805669484335523,
+        "adx": 47.020225174544926
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-06-24 05:30:00",
+      "exit_time": "2025-06-24 08:00:00",
+      "entry_price": 2.184818,
+      "exit_price": 2.167742,
+      "quantity": 2879.5,
+      "sl": 2.167742,
+      "tp": 2.230355,
+      "gross_pnl": -49.171401,
+      "entry_fee": 2.516474,
+      "exit_fee": 2.496805,
+      "net_pnl": -54.18468,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 73.02163697288638,
+        "macd_hist": 0.0005479493365071683,
+        "atr": 0.011384245075129916,
+        "adx": 47.36536786932758
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-07-01 13:00:00",
+      "exit_time": "2025-07-01 14:00:00",
+      "entry_price": 2.185781,
+      "exit_price": 2.19914,
+      "quantity": 3196.0,
+      "sl": 2.19914,
+      "tp": 2.150157,
+      "gross_pnl": -42.695683,
+      "entry_fee": 2.794303,
+      "exit_fee": 2.811381,
+      "net_pnl": -48.301367,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 34.25494593254047,
+        "macd_hist": -0.00014675405719808375,
+        "atr": 0.008906066514248343,
+        "adx": 38.40722178323835
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-07-04 06:00:00",
+      "exit_time": "2025-07-04 08:15:00",
+      "entry_price": 2.232877,
+      "exit_price": 2.208013,
+      "quantity": 3379.7,
+      "sl": 2.242201,
+      "tp": 2.208013,
+      "gross_pnl": 84.031619,
+      "entry_fee": 3.018581,
+      "exit_fee": 2.984969,
+      "net_pnl": 78.028069,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 31.442919224174045,
+        "macd_hist": -0.00029321477558042104,
+        "atr": 0.0062159081353788895,
+        "adx": 33.56850119916028
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-05 19:45:00",
+      "exit_time": "2025-09-05 22:15:00",
+      "entry_price": 2.863514,
+      "exit_price": 2.815423,
+      "quantity": 3491.9,
+      "sl": 2.881548,
+      "tp": 2.815423,
+      "gross_pnl": 167.927076,
+      "entry_fee": 3.999641,
+      "exit_fee": 3.93247,
+      "net_pnl": 159.994965,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 66.8667614741176,
+        "macd_hist": 0.005566660638547516,
+        "atr": 0.012022614930199287,
+        "adx": 25.794325095274626
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-07 07:30:00",
+      "exit_time": "2025-09-07 10:15:00",
+      "entry_price": 2.831483,
+      "exit_price": 2.825709,
+      "quantity": 3310.6,
+      "sl": 2.825709,
+      "tp": 2.846882,
+      "gross_pnl": -19.117005,
+      "entry_fee": 3.749563,
+      "exit_fee": 3.741916,
+      "net_pnl": -26.608485,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 70.72939012092385,
+        "macd_hist": 0.00013947818915852105,
+        "atr": 0.0038496557346203194,
+        "adx": 25.87514662158794
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-07 14:15:00",
+      "exit_time": "2025-09-07 14:30:00",
+      "entry_price": 2.888611,
+      "exit_price": 2.907326,
+      "quantity": 3295.3,
+      "sl": 2.907326,
+      "tp": 2.838705,
+      "gross_pnl": -61.671288,
+      "entry_fee": 3.807536,
+      "exit_fee": 3.832205,
+      "net_pnl": -69.311028,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 76.27147788789821,
+        "macd_hist": 0.006331113894477991,
+        "atr": 0.012476615713124774,
+        "adx": 29.135371839765913
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-09 07:00:00",
+      "exit_time": "2025-09-09 07:15:00",
+      "entry_price": 3.009099,
+      "exit_price": 3.026836,
+      "quantity": 3264.0,
+      "sl": 3.026836,
+      "tp": 2.9618,
+      "gross_pnl": -57.893469,
+      "entry_fee": 3.92868,
+      "exit_fee": 3.951837,
+      "net_pnl": -65.773986,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 73.38194905544675,
+        "macd_hist": 0.006160466326798137,
+        "atr": 0.011824646391069867,
+        "adx": 28.105801823891394
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-12 20:45:00",
+      "exit_time": "2025-09-13 08:45:00",
+      "entry_price": 3.121788,
+      "exit_price": 3.143446,
+      "quantity": 3197.5,
+      "sl": 3.143446,
+      "tp": 3.064033,
+      "gross_pnl": -69.251372,
+      "entry_fee": 3.992767,
+      "exit_fee": 4.020467,
+      "net_pnl": -77.264606,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 78.88995114530964,
+        "macd_hist": 0.004793783646225545,
+        "atr": 0.014438649390670705,
+        "adx": 33.848649235778474
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-14 11:15:00",
+      "exit_time": "2025-09-14 13:45:00",
+      "entry_price": 3.066993,
+      "exit_price": 3.033085,
+      "quantity": 3002.8,
+      "sl": 3.079709,
+      "tp": 3.033085,
+      "gross_pnl": 101.818765,
+      "entry_fee": 3.683827,
+      "exit_fee": 3.643099,
+      "net_pnl": 94.491838,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 31.419480021379645,
+        "macd_hist": -0.0003629091436070245,
+        "atr": 0.008476985221720718,
+        "adx": 31.882046477112183
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-20 14:00:00",
+      "exit_time": "2025-09-20 14:45:00",
+      "entry_price": 2.971603,
+      "exit_price": 2.980986,
+      "quantity": 3353.4,
+      "sl": 2.980986,
+      "tp": 2.94658,
+      "gross_pnl": -31.466181,
+      "entry_fee": 3.985989,
+      "exit_fee": 3.998576,
+      "net_pnl": -39.450746,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 36.09553473183674,
+        "macd_hist": -0.00018720159437711752,
+        "atr": 0.006255577606168083,
+        "adx": 28.84076206692945
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-24 19:45:00",
+      "exit_time": "2025-09-24 20:30:00",
+      "entry_price": 2.976198,
+      "exit_price": 2.955734,
+      "quantity": 3279.9,
+      "sl": 2.955734,
+      "tp": 3.030766,
+      "gross_pnl": -67.117005,
+      "entry_fee": 3.904652,
+      "exit_fee": 3.877805,
+      "net_pnl": -74.899463,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 77.25608496751632,
+        "macd_hist": 0.00019635721897620986,
+        "atr": 0.013642083686890932,
+        "adx": 66.36435142210216
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-25 12:15:00",
+      "exit_time": "2025-09-25 12:30:00",
+      "entry_price": 2.793221,
+      "exit_price": 2.811993,
+      "quantity": 3226.0,
+      "sl": 2.811993,
+      "tp": 2.743161,
+      "gross_pnl": -60.559206,
+      "entry_fee": 3.604372,
+      "exit_fee": 3.628596,
+      "net_pnl": -67.792174,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 27.256149561284357,
+        "macd_hist": -0.0005773233003328118,
+        "atr": 0.012514818420656685,
+        "adx": 36.706433983392714
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-28 22:00:00",
+      "exit_time": "2025-09-29 07:15:00",
+      "entry_price": 2.850785,
+      "exit_price": 2.885643,
+      "quantity": 2923.6,
+      "sl": 2.837713,
+      "tp": 2.885643,
+      "gross_pnl": 101.910302,
+      "entry_fee": 3.333822,
+      "exit_fee": 3.374586,
+      "net_pnl": 95.201894,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 69.94607598871028,
+        "macd_hist": 0.0002172037763433672,
+        "atr": 0.008714453238038499,
+        "adx": 45.96715774504039
+      },
+      "fold": 2
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-12-10 10:30:00",
+      "exit_time": "2025-12-10 18:30:00",
+      "entry_price": 2.069993,
+      "exit_price": 2.080244,
+      "quantity": 4830.5,
+      "sl": 2.080244,
+      "tp": 2.042658,
+      "gross_pnl": -49.515419,
+      "entry_fee": 3.99964,
+      "exit_fee": 4.019447,
+      "net_pnl": -57.534506,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 37.038012691554805,
+        "macd_hist": -9.211636302669133e-05,
+        "atr": 0.0068337189344636114,
+        "adx": 28.943927763667713
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-12-12 16:00:00",
+      "exit_time": "2025-12-13 05:00:00",
+      "entry_price": 1.988899,
+      "exit_price": 2.037103,
+      "quantity": 4739.1,
+      "sl": 1.970822,
+      "tp": 2.037103,
+      "gross_pnl": 228.445099,
+      "entry_fee": 3.770236,
+      "exit_fee": 3.861614,
+      "net_pnl": 220.813249,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 28.182013495720106,
+        "macd_hist": -0.00643391832048344,
+        "atr": 0.01205108033747697,
+        "adx": 30.769786891839054
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-12-19 13:15:00",
+      "exit_time": "2025-12-19 15:15:00",
+      "entry_price": 1.878712,
+      "exit_price": 1.889911,
+      "quantity": 4978.2,
+      "sl": 1.889911,
+      "tp": 1.84885,
+      "gross_pnl": -55.748245,
+      "entry_fee": 3.741042,
+      "exit_fee": 3.763341,
+      "net_pnl": -63.252628,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 68.16547032772114,
+        "macd_hist": -4.5929936914913816e-05,
+        "atr": 0.007465649526915487,
+        "adx": 40.69667585881617
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-12-25 23:30:00",
+      "exit_time": "2025-12-26 02:15:00",
+      "entry_price": 1.831783,
+      "exit_price": 1.857641,
+      "quantity": 5284.9,
+      "sl": 1.822086,
+      "tp": 1.857641,
+      "gross_pnl": 136.657597,
+      "entry_fee": 3.872316,
+      "exit_fee": 3.926979,
+      "net_pnl": 128.858301,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 18.688435627302994,
+        "macd_hist": -0.0034657628634239823,
+        "atr": 0.006464530874639477,
+        "adx": 30.228290924248867
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2026-01-01 15:45:00",
+      "exit_time": "2026-01-01 16:15:00",
+      "entry_price": 1.861986,
+      "exit_price": 1.855307,
+      "quantity": 4787.6,
+      "sl": 1.855307,
+      "tp": 1.879797,
+      "gross_pnl": -31.976479,
+      "entry_fee": 3.565778,
+      "exit_fee": 3.552987,
+      "net_pnl": -39.095244,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 64.9515011671277,
+        "macd_hist": 8.017825296896758e-05,
+        "atr": 0.004452680396625609,
+        "adx": 29.061543249865803
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2026-01-02 14:30:00",
+      "exit_time": "2026-01-02 16:15:00",
+      "entry_price": 1.906991,
+      "exit_price": 1.93559,
+      "quantity": 4818.6,
+      "sl": 1.896266,
+      "tp": 1.93559,
+      "gross_pnl": 137.806916,
+      "entry_fee": 3.67561,
+      "exit_fee": 3.730733,
+      "net_pnl": 130.400573,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 68.243618769103,
+        "macd_hist": 0.00021763021087121363,
+        "atr": 0.007149738287103824,
+        "adx": 34.75978288472445
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2026-01-04 00:45:00",
+      "exit_time": "2026-01-04 03:00:00",
+      "entry_price": 2.041396,
+      "exit_price": 2.038904,
+      "quantity": 3981.9,
+      "sl": 2.052244,
+      "tp": 2.012468,
+      "gross_pnl": 9.922775,
+      "entry_fee": 3.251454,
+      "exit_fee": 3.247485,
+      "net_pnl": 3.423837,
+      "close_reason": "REVERSE_SIGNAL",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 78.42031027026397,
+        "macd_hist": 0.002773445174521872,
+        "atr": 0.007231967338050755,
+        "adx": 25.06146716762975
+      },
+      "fold": 3
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2026-01-04 03:00:00",
+      "exit_time": "2026-01-04 05:15:00",
+      "entry_price": 2.038904,
+      "exit_price": 2.068362,
+      "quantity": 3971.2,
+      "sl": 2.027857,
+      "tp": 2.068362,
+      "gross_pnl": 116.983697,
+      "entry_fee": 3.238758,
+      "exit_fee": 3.285551,
+      "net_pnl": 110.459388,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 66.00101725582081,
+        "macd_hist": 4.503977849404806e-05,
+        "atr": 0.007364505506906315,
+        "adx": 30.991168735172053
+      },
+      "fold": 3
+    }
+  ],
+  "validation": {
+    "overall": "FAIL",
+    "checks": [
+      {
+        "name": "exit_after_entry",
+        "passed": true,
+        "level": "FAIL",
+        "message": "모든 트레이드에서 청산 > 진입"
+      },
+      {
+        "name": "sl_tp_direction",
+        "passed": true,
+        "level": "FAIL",
+        "message": "SL/TP 방향 정합"
+      },
+      {
+        "name": "no_overlap",
+        "passed": true,
+        "level": "FAIL",
+        "message": "포지션 비중첩 확인"
+      },
+      {
+        "name": "positive_fees",
+        "passed": true,
+        "level": "FAIL",
+        "message": "수수료 양수 확인"
+      },
+      {
+        "name": "no_negative_balance",
+        "passed": true,
+        "level": "FAIL",
+        "message": "잔고 양수 유지"
+      },
+      {
+        "name": "win_rate_high",
+        "passed": true,
+        "level": "WARNING",
+        "message": "승률 정상 (44.4%)"
+      },
+      {
+        "name": "win_rate_low",
+        "passed": true,
+        "level": "WARNING",
+        "message": "승률 정상 (44.4%)"
+      },
+      {
+        "name": "mdd_nonzero",
+        "passed": true,
+        "level": "WARNING",
+        "message": "MDD 정상 (20.2%)"
+      },
+      {
+        "name": "trade_frequency",
+        "passed": false,
+        "level": "WARNING",
+        "message": "월 평균 4.0건 < 5건 — 신호 생성 부족"
+      },
+      {
+        "name": "profit_factor_high",
+        "passed": true,
+        "level": "WARNING",
+        "message": "PF 정상 (1.94)"
+      }
+    ]
+  }
+}
--- a/results/xrpusdt/wf_backtest_20260322_231837.json
+++ b/results/xrpusdt/wf_backtest_20260322_231837.json
@@ -0,0 +1,537 @@
+{
+  "mode": "walk_forward",
+  "config": {
+    "symbols": [
+      "XRPUSDT"
+    ],
+    "start": null,
+    "end": null,
+    "initial_balance": 1000.0,
+    "leverage": 10,
+    "fee_pct": 0.04,
+    "slippage_pct": 0.01,
+    "use_ml": false,
+    "ml_threshold": 0.55,
+    "max_daily_loss_pct": 0.05,
+    "max_positions": 3,
+    "max_same_direction": 2,
+    "margin_max_ratio": 0.5,
+    "margin_min_ratio": 0.2,
+    "margin_decay_rate": 0.0006,
+    "atr_sl_mult": 1.5,
+    "atr_tp_mult": 4.0,
+    "min_notional": 5.0,
+    "signal_threshold": 3,
+    "adx_threshold": 25.0,
+    "volume_multiplier": 1.5,
+    "train_months": 6,
+    "test_months": 1,
+    "time_weight_decay": 2.0,
+    "negative_ratio": 3
+  },
+  "summary": {
+    "total_trades": 16,
+    "total_pnl": -130.1928,
+    "return_pct": -13.02,
+    "win_rate": 25.0,
+    "avg_win": 65.5037,
+    "avg_loss": -32.684,
+    "payoff_ratio": 2.0,
+    "max_consecutive_losses": 5,
+    "profit_factor": 0.67,
+    "max_drawdown_pct": 19.46,
+    "sharpe_ratio": -34.26,
+    "total_fees": 61.4728,
+    "close_reasons": {
+      "TAKE_PROFIT": 4,
+      "STOP_LOSS": 11,
+      "REVERSE_SIGNAL": 1
+    }
+  },
+  "folds": [
+    {
+      "fold": 1,
+      "train_period": "2025-03-05 ~ 2025-09-05",
+      "test_period": "2025-09-05 ~ 2025-10-05",
+      "test_start": "2025-09-05T15:00:00",
+      "test_end": "2025-10-05T15:00:00",
+      "summary": {
+        "total_trades": 16,
+        "total_pnl": -130.1928,
+        "return_pct": -13.02,
+        "win_rate": 25.0,
+        "avg_win": 65.5037,
+        "avg_loss": -32.684,
+        "payoff_ratio": 2.0,
+        "max_consecutive_losses": 5,
+        "profit_factor": 0.67,
+        "max_drawdown_pct": 19.46,
+        "sharpe_ratio": -34.26,
+        "total_fees": 61.4728,
+        "close_reasons": {
+          "TAKE_PROFIT": 4,
+          "STOP_LOSS": 11,
+          "REVERSE_SIGNAL": 1
+        }
+      },
+      "market_context": {
+        "btc_return_pct": 11.2,
+        "eth_return_pct": 5.8,
+        "btc_avg_adx": 24.6,
+        "market_regime": "횡보",
+        "ls_ratio": null
+      }
+    }
+  ],
+  "trades": [
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-05 19:45:00",
+      "exit_time": "2025-09-05 22:15:00",
+      "entry_price": 2.863514,
+      "exit_price": 2.815423,
+      "quantity": 1745.9,
+      "sl": 2.881548,
+      "tp": 2.815423,
+      "gross_pnl": 83.961134,
+      "entry_fee": 1.999763,
+      "exit_fee": 1.966179,
+      "net_pnl": 79.995191,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 66.8667614741176,
+        "macd_hist": 0.005566660638547516,
+        "atr": 0.012022614930199287,
+        "adx": 25.794325095274626
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-07 07:30:00",
+      "exit_time": "2025-09-07 10:15:00",
+      "entry_price": 2.831483,
+      "exit_price": 2.825709,
+      "quantity": 1724.2,
+      "sl": 2.825709,
+      "tp": 2.846882,
+      "gross_pnl": -9.956365,
+      "entry_fee": 1.952817,
+      "exit_fee": 1.948835,
+      "net_pnl": -13.858017,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 70.72939012092385,
+        "macd_hist": 0.00013947818915852105,
+        "atr": 0.0038496557346203194,
+        "adx": 25.87514662158794
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-07 14:15:00",
+      "exit_time": "2025-09-07 14:30:00",
+      "entry_price": 2.888611,
+      "exit_price": 2.907326,
+      "quantity": 1698.8,
+      "sl": 2.907326,
+      "tp": 2.838705,
+      "gross_pnl": -31.792912,
+      "entry_fee": 1.962869,
+      "exit_fee": 1.975586,
+      "net_pnl": -35.731367,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 76.27147788789821,
+        "macd_hist": 0.006331113894477991,
+        "atr": 0.012476615713124774,
+        "adx": 29.135371839765913
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-09 07:00:00",
+      "exit_time": "2025-09-09 07:15:00",
+      "entry_price": 3.009099,
+      "exit_price": 3.026836,
+      "quantity": 1649.5,
+      "sl": 3.026836,
+      "tp": 2.9618,
+      "gross_pnl": -29.257131,
+      "entry_fee": 1.985404,
+      "exit_fee": 1.997106,
+      "net_pnl": -33.239641,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 73.38194905544675,
+        "macd_hist": 0.006160466326798137,
+        "atr": 0.011824646391069867,
+        "adx": 28.105801823891394
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-12 20:45:00",
+      "exit_time": "2025-09-13 08:45:00",
+      "entry_price": 3.121788,
+      "exit_price": 3.143446,
+      "quantity": 1596.9,
+      "sl": 3.143446,
+      "tp": 3.064033,
+      "gross_pnl": -34.585619,
+      "entry_fee": 1.994073,
+      "exit_fee": 2.007907,
+      "net_pnl": -38.587599,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 78.88995114530964,
+        "macd_hist": 0.004793783646225545,
+        "atr": 0.014438649390670705,
+        "adx": 33.848649235778474
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-13 09:15:00",
+      "exit_time": "2025-09-13 09:45:00",
+      "entry_price": 3.161284,
+      "exit_price": 3.177886,
+      "quantity": 1516.0,
+      "sl": 3.177886,
+      "tp": 3.117011,
+      "gross_pnl": -25.169101,
+      "entry_fee": 1.917003,
+      "exit_fee": 1.92707,
+      "net_pnl": -29.013173,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 75.37053214953528,
+        "macd_hist": 0.00511253369858191,
+        "atr": 0.011068206025146562,
+        "adx": 36.52494916026817
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-14 11:15:00",
+      "exit_time": "2025-09-14 13:45:00",
+      "entry_price": 3.066993,
+      "exit_price": 3.033085,
+      "quantity": 1515.3,
+      "sl": 3.079709,
+      "tp": 3.033085,
+      "gross_pnl": 51.380703,
+      "entry_fee": 1.858966,
+      "exit_fee": 1.838414,
+      "net_pnl": 47.683323,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 31.419480021379645,
+        "macd_hist": -0.0003629091436070245,
+        "atr": 0.008476985221720718,
+        "adx": 31.882046477112183
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-14 23:15:00",
+      "exit_time": "2025-09-15 01:30:00",
+      "entry_price": 3.030497,
+      "exit_price": 3.044966,
+      "quantity": 1612.2,
+      "sl": 3.044966,
+      "tp": 2.991913,
+      "gross_pnl": -23.326699,
+      "entry_fee": 1.954307,
+      "exit_fee": 1.963638,
+      "net_pnl": -27.244643,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 41.86565415846166,
+        "macd_hist": -6.680085954976589e-05,
+        "atr": 0.009645907843496216,
+        "adx": 26.821083958033373
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-19 20:00:00",
+      "exit_time": "2025-09-20 06:30:00",
+      "entry_price": 2.988001,
+      "exit_price": 3.002469,
+      "quantity": 1589.5,
+      "sl": 3.002469,
+      "tp": 2.949422,
+      "gross_pnl": -22.995886,
+      "entry_fee": 1.899771,
+      "exit_fee": 1.908969,
+      "net_pnl": -26.804627,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 36.43471826247567,
+        "macd_hist": -0.00020348228213156426,
+        "atr": 0.009644913974796715,
+        "adx": 38.358109484089894
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-20 14:00:00",
+      "exit_time": "2025-09-20 14:45:00",
+      "entry_price": 2.971603,
+      "exit_price": 2.980986,
+      "quantity": 1553.2,
+      "sl": 2.980986,
+      "tp": 2.94658,
+      "gross_pnl": -14.574245,
+      "entry_fee": 1.846197,
+      "exit_fee": 1.852027,
+      "net_pnl": -18.272469,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 36.09553473183674,
+        "macd_hist": -0.00018720159437711752,
+        "atr": 0.006255577606168083,
+        "adx": 28.84076206692945
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-24 14:15:00",
+      "exit_time": "2025-09-24 15:30:00",
+      "entry_price": 2.894089,
+      "exit_price": 2.929027,
+      "quantity": 1563.6,
+      "sl": 2.880988,
+      "tp": 2.929027,
+      "gross_pnl": 54.628771,
+      "entry_fee": 1.810079,
+      "exit_fee": 1.831931,
+      "net_pnl": 50.986761,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 66.07824522998891,
+        "macd_hist": 0.0002837479638076925,
+        "atr": 0.008734454267839082,
+        "adx": 33.216876327535196
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-24 19:45:00",
+      "exit_time": "2025-09-24 20:00:00",
+      "entry_price": 2.976198,
+      "exit_price": 2.963004,
+      "quantity": 1606.1,
+      "sl": 2.955734,
+      "tp": 3.030766,
+      "gross_pnl": -21.190755,
+      "entry_fee": 1.912028,
+      "exit_fee": 1.903552,
+      "net_pnl": -25.006335,
+      "close_reason": "REVERSE_SIGNAL",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 77.25608496751632,
+        "macd_hist": 0.00019635721897620986,
+        "atr": 0.013642083686890932,
+        "adx": 66.36435142210216
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-24 20:00:00",
+      "exit_time": "2025-09-25 01:00:00",
+      "entry_price": 2.963004,
+      "exit_price": 2.90759,
+      "quantity": 1570.7,
+      "sl": 2.983784,
+      "tp": 2.90759,
+      "gross_pnl": 87.037912,
+      "entry_fee": 1.861596,
+      "exit_fee": 1.826781,
+      "net_pnl": 83.349535,
+      "close_reason": "TAKE_PROFIT",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 66.65458359619365,
+        "macd_hist": -7.427449332575442e-05,
+        "atr": 0.013853363423541577,
+        "adx": 67.76721468449082
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "SHORT",
+      "entry_time": "2025-09-25 12:15:00",
+      "exit_time": "2025-09-25 12:30:00",
+      "entry_price": 2.793221,
+      "exit_price": 2.811993,
+      "quantity": 1784.3,
+      "sl": 2.811993,
+      "tp": 2.743161,
+      "gross_pnl": -33.495286,
+      "entry_fee": 1.993577,
+      "exit_fee": 2.006976,
+      "net_pnl": -37.495839,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 27.256149561284357,
+        "macd_hist": -0.0005773233003328118,
+        "atr": 0.012514818420656685,
+        "adx": 36.706433983392714
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-25 17:15:00",
+      "exit_time": "2025-09-25 17:30:00",
+      "entry_price": 2.769777,
+      "exit_price": 2.742807,
+      "quantity": 1763.4,
+      "sl": 2.742807,
+      "tp": 2.841698,
+      "gross_pnl": -47.559642,
+      "entry_fee": 1.95369,
+      "exit_fee": 1.934666,
+      "net_pnl": -51.447998,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 31.610683788190443,
+        "macd_hist": -0.006544986366080717,
+        "atr": 0.01798028133337769,
+        "adx": 26.44006928288656
+      },
+      "fold": 1
+    },
+    {
+      "symbol": "XRPUSDT",
+      "side": "LONG",
+      "entry_time": "2025-09-25 17:45:00",
+      "exit_time": "2025-09-26 11:00:00",
+      "entry_price": 2.736174,
+      "exit_price": 2.705528,
+      "quantity": 1691.1,
+      "sl": 2.705528,
+      "tp": 2.817895,
+      "gross_pnl": -51.824893,
+      "entry_fee": 1.850857,
+      "exit_fee": 1.830127,
+      "net_pnl": -55.505877,
+      "close_reason": "STOP_LOSS",
+      "ml_proba": null,
+      "indicators": {
+        "rsi": 25.044837785333744,
+        "macd_hist": -0.0090419871390266,
+        "atr": 0.020430446659902204,
+        "adx": 30.966856582892532
+      },
+      "fold": 1
+    }
+  ],
+  "validation": {
+    "overall": "PASS",
+    "checks": [
+      {
+        "name": "exit_after_entry",
+        "passed": true,
+        "level": "FAIL",
+        "message": "모든 트레이드에서 청산 > 진입"
+      },
+      {
+        "name": "sl_tp_direction",
+        "passed": true,
+        "level": "FAIL",
+        "message": "SL/TP 방향 정합"
+      },
+      {
+        "name": "no_overlap",
+        "passed": true,
+        "level": "FAIL",
+        "message": "포지션 비중첩 확인"
+      },
+      {
+        "name": "positive_fees",
+        "passed": true,
+        "level": "FAIL",
+        "message": "수수료 양수 확인"
+      },
+      {
+        "name": "no_negative_balance",
+        "passed": true,
+        "level": "FAIL",
+        "message": "잔고 양수 유지"
+      },
+      {
+        "name": "win_rate_high",
+        "passed": true,
+        "level": "WARNING",
+        "message": "승률 정상 (25.0%)"
+      },
+      {
+        "name": "win_rate_low",
+        "passed": true,
+        "level": "WARNING",
+        "message": "승률 정상 (25.0%)"
+      },
+      {
+        "name": "mdd_nonzero",
+        "passed": true,
+        "level": "WARNING",
+        "message": "MDD 정상 (19.5%)"
+      },
+      {
+        "name": "trade_frequency",
+        "passed": true,
+        "level": "WARNING",
+        "message": "월 평균 16.0건"
+      },
+      {
+        "name": "profit_factor_high",
+        "passed": true,
+        "level": "WARNING",
+        "message": "PF 정상 (0.67)"
+      }
+    ]
+  }
+}
--- a/results/xrpusdt/wf_backtest_20260322_232159.json
+++ b/results/xrpusdt/wf_backtest_20260322_232159.json
--- a/scripts/evaluate_oos.py
+++ b/scripts/evaluate_oos.py
@@ -4,10 +4,15 @@ MTF Pullback Bot — OOS Dry-run 평가 스크립트
 프로덕션 서버에서 JSONL 거래 기록을 가져와
 승률·PF·누적PnL·평균보유시간을 계산하고 LIVE 배포 판정을 출력한다.

+비용 모델(수수료·슬리피지·펀딩)을 사후보정으로 적용하여
+fees_only / realistic / pessimistic 3개 시나리오 결과를 출력한다.
+
 Usage:
    python scripts/evaluate_oos.py
    python scripts/evaluate_oos.py --symbol xrpusdt
    python scripts/evaluate_oos.py --local  # 로컬 파일만 사용 (서버 fetch 스킵)
+    python scripts/evaluate_oos.py --local --scenario all
+    python scripts/evaluate_oos.py --local --scenario fees_only
 """

 import argparse
@@ -17,6 +22,10 @@ from pathlib import Path

 import pandas as pd

+# ── 비용 모델 import ─────────────────────────────────────────────
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+from src.config import COST_MODEL, COST_SCENARIOS  # noqa: E402
+
 # ── 설정 ──────────────────────────────────────────────────────────
 PROD_HOST = "root@10.1.10.24"
 REMOTE_DIR = "/root/cointrader/data/trade_history"
@@ -67,20 +76,74 @@ def load_trades(path: Path) -> pd.DataFrame:
    return df


-def calc_metrics(df: pd.DataFrame) -> dict:
+def count_funding_events(entry_ts, exit_ts) -> int:
+    """
+    Binance USDⓈ-M Futures 펀딩 스냅샷 시각(00/08/16 UTC)이
+    [entry_ts, exit_ts] 구간에 몇 번 포함되는지 카운트.
+    """
+    start = entry_ts.ceil("h")
+    end = exit_ts.floor("h")
+    if start > end:
+        return 0
+    hours = pd.date_range(start, end, freq="1h", inclusive="both")
+    return sum(1 for h in hours if h.hour % 8 == 0)
+
+
+def _get_fee_bps(order_type: str) -> float:
+    """주문 타입에 따른 수수료 bps 반환."""
+    if order_type == "taker":
+        return COST_MODEL["taker_fee_bps"]
+    return COST_MODEL["maker_fee_bps"]
+
+
+def calc_trade_cost(row, scenario: dict) -> float:
+    """개별 거래의 총 비용(bps)을 계산."""
+    # 1) Fee: entry + exit
+    entry_fee = _get_fee_bps(COST_MODEL["entry_order_type"])
+
+    # exit order type: SL 히트면 sl_order_type, TP 히트면 tp_order_type
+    reason = row.get("reason", "")
+    if "SL" in reason:
+        exit_fee = _get_fee_bps(COST_MODEL["sl_order_type"])
+    else:
+        exit_fee = _get_fee_bps(COST_MODEL["tp_order_type"])
+
+    fee = entry_fee + exit_fee
+
+    # 2) Slippage: 왕복
+    slippage = scenario["slippage_bps_per_side"] * 2
+
+    # 3) Funding: 경계 교차 카운트
+    funding_count = count_funding_events(row["entry_ts"], row["exit_ts"])
+    funding = funding_count * scenario["funding_bps_per_8h"]
+
+    return fee + slippage + funding
+
+
+def apply_cost_model(df: pd.DataFrame, scenario_name: str) -> pd.DataFrame:
+    """DataFrame에 비용을 적용하여 adjusted_pnl_bps 컬럼 추가."""
+    scenario = COST_SCENARIOS[scenario_name]
+    result = df.copy()
+    result["cost_bps"] = result.apply(lambda row: calc_trade_cost(row, scenario), axis=1)
+    result["adjusted_pnl_bps"] = result["pnl_bps"] - result["cost_bps"]
+    return result
+
+
+def calc_metrics(df: pd.DataFrame, pnl_col: str = "pnl_bps") -> dict:
    """핵심 지표 계산. 빈 DataFrame이면 안전한 기본값 반환."""
    n = len(df)
    if n == 0:
-        return {"trades": 0, "win_rate": 0.0, "pf": 0.0, "cum_pnl": 0.0, "avg_dur": 0.0}
+        return {"trades": 0, "win_rate": 0.0, "pf": 0.0, "cum_pnl": 0.0, "avg_pnl": 0.0, "avg_dur": 0.0}

-    wins = df[df["pnl_bps"] > 0]
-    losses = df[df["pnl_bps"] < 0]
+    wins = df[df[pnl_col] > 0]
+    losses = df[df[pnl_col] < 0]

    win_rate = len(wins) / n * 100
-    gross_profit = wins["pnl_bps"].sum() if len(wins) > 0 else 0.0
-    gross_loss = abs(losses["pnl_bps"].sum()) if len(losses) > 0 else 0.0
+    gross_profit = wins[pnl_col].sum() if len(wins) > 0 else 0.0
+    gross_loss = abs(losses[pnl_col].sum()) if len(losses) > 0 else 0.0
    pf = gross_profit / gross_loss if gross_loss > 0 else float("inf")
-    cum_pnl = df["pnl_bps"].sum()
+    cum_pnl = df[pnl_col].sum()
+    avg_pnl = cum_pnl / n
    avg_dur = df["duration_min"].mean()

    return {
@@ -88,28 +151,29 @@ def calc_metrics(df: pd.DataFrame) -> dict:
        "win_rate": round(win_rate, 1),
        "pf": round(pf, 2),
        "cum_pnl": round(cum_pnl, 1),
+        "avg_pnl": round(avg_pnl, 2),
        "avg_dur": round(avg_dur, 1),
    }


 def print_report(df: pd.DataFrame):
-    """성적표 출력."""
+    """성적표 출력 (raw, 비용 미반영)."""
    total = calc_metrics(df)
    longs = calc_metrics(df[df["side"] == "LONG"])
    shorts = calc_metrics(df[df["side"] == "SHORT"])

    header = f"{'':>10} {'Trades':>8} {'WinRate':>9} {'PF':>8} {'CumPnL':>10} {'AvgDur':>10}"
-    sep = "─" * 60
+    sep = "\u2500" * 60

    print()
    print(sep)
-    print("  MTF Pullback Bot — OOS Dry-run 성적표")
+    print("  MTF Pullback Bot \u2014 OOS Dry-run \uc131\uc801\ud45c")
    print(sep)
    print(header)
    print(sep)

    for label, m in [("Total", total), ("LONG", longs), ("SHORT", shorts)]:
-        pf_str = f"{m['pf']:.2f}" if m["pf"] != float("inf") else "∞"
+        pf_str = f"{m['pf']:.2f}" if m["pf"] != float("inf") else "\u221e"
        dur_str = f"{m['avg_dur']:.0f}m" if m["trades"] > 0 else "-"
        print(
            f"{label:>10} {m['trades']:>8d} {m['win_rate']:>8.1f}% {pf_str:>8} "
@@ -128,46 +192,168 @@ def print_report(df: pd.DataFrame):
        dur = f"{row['duration_min']:.0f}m"
        reason = row.get("reason", "")
        if len(reason) > 25:
-            reason = reason[:25] + "…"
+            reason = reason[:25] + "\u2026"
        print(
            f"{i+1:>3} {row['side']:>6} {row['entry_price']:>10.4f} {row['exit_price']:>10.4f} "
            f"{row['pnl_bps']:>+10.1f} {dur:>8} {reason}"
        )
    print(sep)

-    # ── 최종 판정 ──
+    # ── 최종 판정 (비용 반영 기준) ──
+    # Raw PF는 비현실적 — fees_only 기준으로 판정
+    cost_df = apply_cost_model(df, "fees_only")
+    cost_total = calc_metrics(cost_df, pnl_col="adjusted_pnl_bps")
+    cost_long = calc_metrics(cost_df[cost_df["side"] == "LONG"], pnl_col="adjusted_pnl_bps")
+    cost_short = calc_metrics(cost_df[cost_df["side"] == "SHORT"], pnl_col="adjusted_pnl_bps")
+
+    # 대칭성 체크: LONG/SHORT 양쪽 모두 PF >= 0.8 이상이어야 함
+    symmetry_ok = True
+    if cost_long["trades"] >= 5 and cost_short["trades"] >= 5:
+        symmetry_ok = cost_long["pf"] >= 0.8 and cost_short["pf"] >= 0.8
+
    print()
-    if total["trades"] >= MIN_TRADES and total["pf"] >= MIN_PF:
-        print(f"  [판정: 통과] 엣지가 증명되었습니다. LIVE 배포(자금 투입)를 권장합니다.")
-        print(f"  (거래수 {total['trades']} >= {MIN_TRADES}, PF {total['pf']:.2f} >= {MIN_PF:.1f})")
+    if cost_total["trades"] >= MIN_TRADES and cost_total["pf"] >= MIN_PF and symmetry_ok:
+        print(f"  [\ud310\uc815: \ud1b5\uacfc] \uc5e3\uc9c0\uac00 \uc99d\uba85\ub418\uc5c8\uc2b5\ub2c8\ub2e4. LIVE \ubc30\ud3ec(\uc790\uae08 \ud22c\uc785)\ub97c \uad8c\uc7a5\ud569\ub2c8\ub2e4.")
+        print(f"  (\uac70\ub798\uc218 {cost_total['trades']} >= {MIN_TRADES}, fees_only PF {cost_total['pf']:.2f} >= {MIN_PF:.1f})")
    else:
        reasons = []
-        if total["trades"] < MIN_TRADES:
-            reasons.append(f"거래수 {total['trades']} < {MIN_TRADES}")
-        if total["pf"] < MIN_PF:
-            reasons.append(f"PF {total['pf']:.2f} < {MIN_PF:.1f}")
-        print(f"  [판정: 보류] 기준 미달. OOS 검증 실패로 실전 투입을 보류합니다.")
+        if cost_total["trades"] < MIN_TRADES:
+            reasons.append(f"\uac70\ub798\uc218 {cost_total['trades']} < {MIN_TRADES}")
+        if cost_total["pf"] < MIN_PF:
+            reasons.append(f"fees_only PF {cost_total['pf']:.2f} < {MIN_PF:.1f}")
+        if not symmetry_ok:
+            reasons.append(f"LONG/SHORT \ube44\ub300\uce6d (L:{cost_long['pf']:.2f} / S:{cost_short['pf']:.2f})")
+        print(f"  [\ud310\uc815: \uc2e4\ud328] OOS \uac80\uc99d \uc2e4\ud328. \uc2e4\uc804 \ud22c\uc785 \ubd88\uac00.")
        print(f"  ({', '.join(reasons)})")
    print()


+def print_cost_report(df: pd.DataFrame, scenario_names: list[str]):
+    """비용 보정 시나리오별 성적표 출력."""
+    sep = "\u2500" * 61
+
+    # 시나리오별 데이터 준비
+    scenario_dfs = {}
+    for name in scenario_names:
+        scenario_dfs[name] = apply_cost_model(df, name)
+
+    print()
+    print(sep)
+    print("  MTF Pullback Bot \u2014 OOS Cost-Adjusted Results")
+    print(sep)
+
+    # 헤더
+    header = f"{'Scenario:':>16}"
+    for name in scenario_names:
+        header += f" {name:>14}"
+    print(header)
+    print(sep)
+
+    # Total / LONG / SHORT 각각
+    for section_label, filter_fn in [
+        ("Total", lambda d: d),
+        ("LONG", lambda d: d[d["side"] == "LONG"]),
+        ("SHORT", lambda d: d[d["side"] == "SHORT"]),
+    ]:
+        print(section_label)
+
+        # 각 시나리오에 대해 metrics 계산
+        metrics_list = []
+        for name in scenario_names:
+            sdf = filter_fn(scenario_dfs[name])
+            m = calc_metrics(sdf, pnl_col="adjusted_pnl_bps")
+            metrics_list.append(m)
+
+        # Trades
+        line = f"{'Trades:':>16}"
+        for m in metrics_list:
+            line += f" {m['trades']:>14d}"
+        print(line)
+
+        # WinRate
+        line = f"{'WinRate:':>16}"
+        for m in metrics_list:
+            line += f" {m['win_rate']:>13.1f}%"
+        print(line)
+
+        # PF
+        line = f"{'PF:':>16}"
+        for m in metrics_list:
+            pf_str = f"{m['pf']:.2f}" if m["pf"] != float("inf") else "\u221e"
+            line += f" {pf_str:>14}"
+        print(line)
+
+        # CumPnL(bps)
+        line = f"{'CumPnL(bps):':>16}"
+        for m in metrics_list:
+            line += f" {m['cum_pnl']:>+14.1f}"
+        print(line)
+
+        # AvgPnL(bps)
+        line = f"{'AvgPnL(bps):':>16}"
+        for m in metrics_list:
+            line += f" {m['avg_pnl']:>+14.2f}"
+        print(line)
+
+        # AvgDur
+        line = f"{'AvgDur:':>16}"
+        for m in metrics_list:
+            dur_str = f"{m['avg_dur']:.0f}m" if m["trades"] > 0 else "-"
+            line += f" {dur_str:>14}"
+        print(line)
+
+    print(sep)
+
+    # Raw 참고
+    raw_total = calc_metrics(df)
+    print(f"Raw (\ube44\uc6a9 \ubbf8\ubc18\uc601, \ucc38\uace0\uc6a9):")
+    pf_str = f"{raw_total['pf']:.2f}" if raw_total["pf"] != float("inf") else "\u221e"
+    print(f"  Total PF: {pf_str}, CumPnL: {raw_total['cum_pnl']:+.1f} bps")
+    print(sep)
+    print()
+
+
 def main():
-    parser = argparse.ArgumentParser(description="MTF OOS Dry-run 평가")
-    parser.add_argument("--symbol", default="xrpusdt", help="심볼 (파일명 소문자, 기본: xrpusdt)")
-    parser.add_argument("--local", action="store_true", help="로컬 파일만 사용 (서버 fetch 스킵)")
+    parser = argparse.ArgumentParser(description="MTF OOS Dry-run \ud3c9\uac00")
+    parser.add_argument("--symbol", default="xrpusdt", help="\uc2ec\ubcfc (\ud30c\uc77c\uba85 \uc18c\ubb38\uc790, \uae30\ubcf8: xrpusdt)")
+    parser.add_argument("--local", action="store_true", help="\ub85c\uceec \ud30c\uc77c\ub9cc \uc0ac\uc6a9 (\uc11c\ubc84 fetch \uc2a4\ud0b5)")
+    parser.add_argument(
+        "--scenario",
+        choices=["fees_only", "realistic", "pessimistic", "all"],
+        default="all",
+        help="\ube44\uc6a9 \ubcf4\uc815 \uc2dc\ub098\ub9ac\uc624 (\uae30\ubcf8: all)",
+    )
    args = parser.parse_args()

-    filename = f"mtf_{args.symbol}.jsonl"
+    # MTF bot은 ccxt 심볼(XRP/USDT:USDT)에서 /,:를 제거하여 파일명 생성
+    # → mtf_xrpusdtusdt.jsonl  (심볼 인자 xrpusdt → xrpusdtusdt 변환)
+    raw = args.symbol.lower()
+    if not raw.endswith("usdt"):
+        raw = raw + "usdt"
+    # xrpusdt → xrpusdtusdt (ccxt 포맷 XRP/USDT:USDT 의 슬래시·콜론 제거 결과)
+    if raw.endswith("usdt") and not raw.endswith("usdtusdt"):
+        raw = raw + "usdt"
+    filename = f"mtf_{raw}.jsonl"

    if args.local:
        local_path = LOCAL_DIR / filename
        if not local_path.exists():
-            print(f"[Error] 로컬 파일 없음: {local_path}")
+            print(f"[Error] \ub85c\uceec \ud30c\uc77c \uc5c6\uc74c: {local_path}")
            sys.exit(1)
    else:
        local_path = fetch_from_prod(filename)

    df = load_trades(local_path)
+
+    # 비용 보정 리포트 출력
+    if args.scenario == "all":
+        scenario_names = ["fees_only", "realistic", "pessimistic"]
+    else:
+        scenario_names = [args.scenario]
+
+    print_cost_report(df, scenario_names)
+
+    # raw 리포트도 하단에 유지
    print_report(df)


--- a/scripts/fr_oi_backtest.py
+++ b/scripts/fr_oi_backtest.py
@@ -0,0 +1,364 @@
+"""
+FR × OI 변화율 백테스트 — Phase 1: 12개 조합
+
+신호: FR × OI변화율(1h) = funding_rate × oi_pct_change_4
+- SHORT: 피처 >= threshold (롱 스퀴즈 전조)
+- LONG: 피처 <= threshold (숏 스퀴즈 전조)
+- 보유: 1h(4캔들) / 4h(16캔들)
+
+Usage: python scripts/fr_oi_backtest.py
+"""
+
+import asyncio
+import aiohttp
+import pandas as pd
+import numpy as np
+from datetime import datetime, timedelta, timezone
+from pathlib import Path
+
+BASE = "https://fapi.binance.com"
+SYMBOL = "XRPUSDT"
+DATA_DIR = Path("data/xrpusdt")
+FEE_RATE = 0.0004
+
+
+async def fetch_oi_history(session, symbol, start_ms, end_ms):
+    all_data = []
+    current = start_ms
+    calls = 0
+    while current < end_ms:
+        params = {"symbol": symbol, "period": "15m", "startTime": current, "endTime": end_ms, "limit": 500}
+        async with session.get(f"{BASE}/futures/data/openInterestHist", params=params) as resp:
+            data = await resp.json()
+        if not data or not isinstance(data, list):
+            break
+        all_data.extend(data)
+        last_ts = int(data[-1]["timestamp"])
+        if last_ts <= current:
+            break
+        current = last_ts + 1
+        calls += 1
+        if calls % 50 == 0:
+            await asyncio.sleep(5)
+        else:
+            await asyncio.sleep(0.1)
+    if not all_data:
+        return pd.DataFrame()
+    df = pd.DataFrame(all_data)
+    df["timestamp"] = pd.to_datetime(df["timestamp"].astype(int), unit="ms", utc=True)
+    df["oi_value"] = df["sumOpenInterestValue"].astype(float)
+    return df[["timestamp", "oi_value"]].drop_duplicates("timestamp").sort_values("timestamp")
+
+
+async def fetch_funding_rate(session, symbol, start_ms, end_ms):
+    all_data = []
+    current = start_ms
+    while current < end_ms:
+        params = {"symbol": symbol, "startTime": current, "endTime": end_ms, "limit": 1000}
+        async with session.get(f"{BASE}/fapi/v1/fundingRate", params=params) as resp:
+            data = await resp.json()
+        if not data or not isinstance(data, list):
+            break
+        all_data.extend(data)
+        last_ts = int(data[-1]["fundingTime"])
+        if last_ts <= current:
+            break
+        current = last_ts + 1
+        await asyncio.sleep(0.1)
+    if not all_data:
+        return pd.DataFrame()
+    df = pd.DataFrame(all_data)
+    df["timestamp"] = pd.to_datetime(df["fundingTime"].astype(int), unit="ms", utc=True)
+    df["funding_rate"] = df["fundingRate"].astype(float)
+    return df[["timestamp", "funding_rate"]].drop_duplicates("timestamp").sort_values("timestamp")
+
+
+def run_backtest(df, feature_col, percentile, direction, hold_bars):
+    threshold = df[feature_col].quantile(percentile / 100)
+    trades = []
+    i = 0
+    while i < len(df) - hold_bars - 1:
+        val = df.iloc[i][feature_col]
+        if pd.isna(val):
+            i += 1
+            continue
+
+        trigger = False
+        if direction == "SHORT" and val >= threshold:
+            trigger = True
+        elif direction == "LONG" and val <= threshold:
+            trigger = True
+
+        if trigger:
+            entry_idx = i + 1
+            exit_idx = i + 1 + hold_bars - 1
+            if exit_idx >= len(df):
+                break
+            entry_price = df.iloc[entry_idx]["open"]
+            exit_price = df.iloc[exit_idx]["close"]
+
+            if direction == "LONG":
+                gross_return = (exit_price / entry_price) - 1
+            else:
+                gross_return = (entry_price / exit_price) - 1
+
+            fee = FEE_RATE * 2
+            net_return = gross_return - fee
+
+            trades.append({
+                "entry_time": df.iloc[entry_idx]["timestamp"],
+                "exit_time": df.iloc[exit_idx]["timestamp"],
+                "entry_price": entry_price,
+                "exit_price": exit_price,
+                "feature_val": val,
+                "gross_return_bps": gross_return * 10000,
+                "net_return_bps": net_return * 10000,
+            })
+            i = exit_idx + 1  # 포지션 종료 후 다음
+        else:
+            i += 1
+
+    if not trades:
+        return None
+
+    tdf = pd.DataFrame(trades)
+    wins = tdf[tdf["net_return_bps"] > 0]["net_return_bps"]
+    losses = tdf[tdf["net_return_bps"] <= 0]["net_return_bps"]
+
+    gross_profit = wins.sum() if len(wins) > 0 else 0
+    gross_loss = abs(losses.sum()) if len(losses) > 0 else 0
+    pf = gross_profit / gross_loss if gross_loss > 0 else float("inf") if gross_profit > 0 else 0
+
+    cum_pnl = tdf["net_return_bps"].cumsum()
+    max_dd = (cum_pnl - cum_pnl.cummax()).min()
+
+    return {
+        "trades": len(tdf),
+        "wins": len(wins),
+        "losses": len(losses),
+        "win_rate": len(wins) / len(tdf) * 100,
+        "pf": pf,
+        "total_pnl_bps": tdf["net_return_bps"].sum(),
+        "avg_pnl_bps": tdf["net_return_bps"].mean(),
+        "max_dd_bps": max_dd,
+        "threshold": threshold,
+        "df_trades": tdf,
+    }
+
+
+def confidence(n):
+    if n < 20:
+        return "🔴", "폐기"
+    elif n < 50:
+        return "🟡", "참고"
+    else:
+        return "🟢", "검토"
+
+
+async def main():
+    print("=" * 80)
+    print("  FR × OI 변화율 백테스트 — Phase 1: 12개 조합")
+    print("=" * 80)
+
+    # 데이터 수집
+    print("\n[1] 데이터 수집")
+    df_kline = pd.read_parquet(DATA_DIR / "combined_15m.parquet")
+
+    end_dt = datetime.now(timezone.utc)
+    oi_start_dt = end_dt - timedelta(days=29)
+    oi_start_ms = int(oi_start_dt.replace(microsecond=0, second=0).timestamp()) * 1000
+    fr_start_ms = oi_start_ms
+    end_ms = int(end_dt.replace(microsecond=0, second=0).timestamp()) * 1000
+
+    async with aiohttp.ClientSession() as session:
+        print("  OI 수집...")
+        oi_df = await fetch_oi_history(session, SYMBOL, oi_start_ms, end_ms)
+        print(f"  OI: {len(oi_df)} rows")
+        print("  FR 수집...")
+        fr_df = await fetch_funding_rate(session, SYMBOL, fr_start_ms, end_ms)
+        print(f"  FR: {len(fr_df)} rows")
+
+    # 병합
+    print("\n[2] 데이터 병합")
+    df = df_kline.loc[oi_start_dt:].copy().reset_index()
+    print(f"  Kline (29일): {len(df)} rows")
+
+    # OI 병합
+    df = pd.merge_asof(df.sort_values("timestamp"), oi_df.sort_values("timestamp"),
+                       on="timestamp", direction="nearest", tolerance=pd.Timedelta(minutes=20))
+    df["oi_pct_change_4"] = df["oi_value"].pct_change(4)
+
+    # FR 병합 (forward fill)
+    df = pd.merge_asof(df.sort_values("timestamp"), fr_df.rename(columns={"funding_rate": "fr_api"}).sort_values("timestamp"),
+                       on="timestamp", direction="backward")
+
+    # 핵심 피처: FR × OI변화율(1h)
+    df["fr_x_oi_1h"] = df["fr_api"] * df["oi_pct_change_4"]
+
+    valid = df.dropna(subset=["fr_x_oi_1h"])
+    print(f"  유효 데이터: {len(valid)} rows")
+    print(f"  fr_x_oi_1h: mean={valid['fr_x_oi_1h'].mean():.8f}, std={valid['fr_x_oi_1h'].std():.8f}")
+
+    for p in [25, 50, 75]:
+        v = valid["fr_x_oi_1h"].quantile(p / 100)
+        print(f"  P{p}: {v:.8f}")
+
+    # 12개 조합 백테스트
+    print("\n[3] 12개 조합 백테스트")
+    print("=" * 80)
+
+    combos = []
+    for hold_label, hold_bars in [("1h", 4), ("4h", 16)]:
+        for direction in ["SHORT", "LONG"]:
+            for pct in [75, 50, 25]:
+                desc_dir = "롱스퀴즈" if direction == "SHORT" else "숏스퀴즈"
+                combos.append({
+                    "hold_label": hold_label,
+                    "hold_bars": hold_bars,
+                    "direction": direction,
+                    "percentile": pct,
+                    "desc": f"{direction} {hold_label} P{pct} ({desc_dir})",
+                })
+
+    results = []
+    for c in combos:
+        r = run_backtest(valid.reset_index(drop=True), "fr_x_oi_1h",
+                         c["percentile"], c["direction"], c["hold_bars"])
+        if r:
+            r.update(c)
+        else:
+            r = {**c, "trades": 0, "wins": 0, "losses": 0, "win_rate": 0,
+                 "pf": 0, "total_pnl_bps": 0, "avg_pnl_bps": 0, "max_dd_bps": 0, "threshold": 0}
+        results.append(r)
+
+    # 결과 테이블
+    print(f"\n{'ID':>3} {'조합':<28} {'거래수':>6} {'승률':>7} {'PF':>7} {'PnL(bps)':>10} {'MaxDD':>10} {'신뢰도'}")
+    print("-" * 90)
+
+    for i, r in enumerate(results, 1):
+        emoji, label = confidence(r["trades"])
+        pf_str = f"{r['pf']:.2f}" if r["pf"] != float("inf") else "INF"
+        print(f"{i:>3} {r['desc']:<28} {r['trades']:>6} {r['win_rate']:>6.1f}% {pf_str:>7} "
+              f"{r['total_pnl_bps']:>+10.1f} {r['max_dd_bps']:>10.1f} {emoji} {label}")
+
+    # 대칭성 검증
+    print("\n" + "=" * 80)
+    print("  [대칭성 검증]")
+    print("=" * 80)
+
+    for hold_label in ["1h", "4h"]:
+        shorts = [r for r in results if r["hold_label"] == hold_label and r["direction"] == "SHORT" and r["trades"] > 0]
+        longs = [r for r in results if r["hold_label"] == hold_label and r["direction"] == "LONG" and r["trades"] > 0]
+
+        best_short = max(shorts, key=lambda x: x["pf"]) if shorts else None
+        best_long = max(longs, key=lambda x: x["pf"]) if longs else None
+
+        print(f"\n  [{hold_label} 보유]")
+        if best_short:
+            print(f"    Best SHORT: {best_short['desc']} — PF={best_short['pf']:.2f}, {best_short['trades']}건")
+        if best_long:
+            print(f"    Best LONG:  {best_long['desc']} — PF={best_long['pf']:.2f}, {best_long['trades']}건")
+
+        if best_short and best_long:
+            s_pf = best_short["pf"]
+            l_pf = best_long["pf"]
+            if s_pf > 1.5 and l_pf > 1.5:
+                print(f"    → Case 1: 양방향 생존 ✓ Phase 2 후보")
+            elif (s_pf > 1.5 and l_pf < 0.5) or (l_pf > 1.5 and s_pf < 0.5):
+                print(f"    → Case 2: 한쪽만 성공 ✗ 시장 베타/우연")
+            elif s_pf > 1.5 or l_pf > 1.5:
+                print(f"    → Case 3: 부분적 edge ~ 낮은 신뢰도")
+            elif s_pf > 1.0 and l_pf > 1.0:
+                print(f"    → 양쪽 PF > 1.0이나 < 1.5 — 약한 edge")
+            else:
+                print(f"    → 양쪽 모두 약함")
+
+    # 보유시간 비교
+    print("\n" + "=" * 80)
+    print("  [보유시간 비교]")
+    print("=" * 80)
+
+    for direction in ["SHORT", "LONG"]:
+        r_1h = [r for r in results if r["hold_label"] == "1h" and r["direction"] == direction and r["trades"] > 0]
+        r_4h = [r for r in results if r["hold_label"] == "4h" and r["direction"] == direction and r["trades"] > 0]
+        best_1h = max(r_1h, key=lambda x: x["pf"]) if r_1h else None
+        best_4h = max(r_4h, key=lambda x: x["pf"]) if r_4h else None
+
+        print(f"\n  [{direction}]")
+        if best_1h:
+            print(f"    1h Best: PF={best_1h['pf']:.2f} ({best_1h['desc']}, {best_1h['trades']}건)")
+        if best_4h:
+            print(f"    4h Best: PF={best_4h['pf']:.2f} ({best_4h['desc']}, {best_4h['trades']}건)")
+        if best_1h and best_4h:
+            if best_4h["pf"] > best_1h["pf"]:
+                print(f"    → 4h가 더 강함 (상관분석 r=-0.1734과 일치)")
+            else:
+                print(f"    → 1h가 더 강함 (주의: 상관분석은 4h 기준)")
+
+    # 최종 판정
+    print("\n" + "=" * 80)
+    print("  [최종 판정]")
+    print("=" * 80)
+
+    # Phase 2 후보 찾기
+    phase2 = []
+    for hold_label in ["4h", "1h"]:
+        shorts = [r for r in results if r["hold_label"] == hold_label and r["direction"] == "SHORT" and r["trades"] >= 20]
+        longs = [r for r in results if r["hold_label"] == hold_label and r["direction"] == "LONG" and r["trades"] >= 20]
+
+        best_s = max(shorts, key=lambda x: x["pf"]) if shorts else None
+        best_l = max(longs, key=lambda x: x["pf"]) if longs else None
+
+        if best_s and best_l:
+            if best_s["pf"] > 1.5 and best_l["pf"] > 1.5:
+                phase2.append(("Case1", hold_label, best_s, best_l))
+            elif best_s["pf"] > 1.5 or best_l["pf"] > 1.5:
+                phase2.append(("Case3", hold_label, best_s, best_l))
+
+    if phase2:
+        print(f"\n  🟢 Phase 2 후보 발견!")
+        for case, hl, bs, bl in phase2:
+            print(f"    [{case}] {hl}: SHORT PF={bs['pf']:.2f}({bs['trades']}건), "
+                  f"LONG PF={bl['pf']:.2f}({bl['trades']}건)")
+        print(f"\n  → Phase 2 (Bot Simulation) 진행 권장")
+        print(f"  → 단, 29일 OI 데이터 + 448행 제한 감안")
+    else:
+        all_pf = [(r["desc"], r["pf"], r["trades"]) for r in results if r["trades"] > 0]
+        all_pf.sort(key=lambda x: x[1], reverse=True)
+        best = all_pf[0] if all_pf else ("N/A", 0, 0)
+
+        above_1 = [r for r in results if r["pf"] > 1.0 and r["trades"] >= 20]
+        if above_1:
+            print(f"\n  🟡 PF > 1.0 조합 존재 ({len(above_1)}개), 단 < 1.5")
+            for r in sorted(above_1, key=lambda x: x["pf"], reverse=True):
+                emoji, _ = confidence(r["trades"])
+                print(f"    {r['desc']}: PF={r['pf']:.2f}, {r['trades']}건 {emoji}")
+            print(f"\n  → 약한 edge. 4월 데이터 축적 후 재검증 권장.")
+        else:
+            print(f"\n  🔴 PF > 1.0 조합 없음 (20건 이상)")
+            print(f"    Best: {best[0]} (PF={best[1]:.2f}, {best[2]}건)")
+            print(f"\n  → FR × OI 시그널도 비용 후 edge 없음")
+
+    # Best 조합 상세
+    valid_results = [r for r in results if r["trades"] > 10 and "df_trades" in r]
+    if valid_results:
+        best_r = max(valid_results, key=lambda x: x["pf"])
+        print(f"\n[참고] Best 조합 상세: {best_r['desc']}")
+        print("-" * 60)
+        tdf = best_r["df_trades"]
+        print(f"  기간: {tdf['entry_time'].min()} ~ {tdf['exit_time'].max()}")
+        print(f"  평균 피처값: {tdf['feature_val'].mean():.8f}")
+        w = tdf[tdf["net_return_bps"] > 0]
+        l = tdf[tdf["net_return_bps"] <= 0]
+        if len(w) > 0:
+            print(f"  수익 거래 평균: {w['net_return_bps'].mean():.1f} bps ({len(w)}건)")
+        if len(l) > 0:
+            print(f"  손실 거래 평균: {l['net_return_bps'].mean():.1f} bps ({len(l)}건)")
+
+    print("\n" + "=" * 80)
+    print("  분석 완료.")
+    print("=" * 80)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
--- a/scripts/funding_oi_analysis.py
+++ b/scripts/funding_oi_analysis.py
@@ -0,0 +1,312 @@
+"""
+Funding Rate + OI 변화율 상관분석
+
+기존 combined_15m.parquet에 funding_rate 2년치 있음.
+OI는 Binance API에서 2개월치 수집 후 병합.
+상관분석 → r 값으로 edge 판정.
+
+Usage: python scripts/funding_oi_analysis.py
+"""
+
+import asyncio
+import aiohttp
+import pandas as pd
+import numpy as np
+from datetime import datetime, timedelta, timezone
+from pathlib import Path
+import time
+
+BASE = "https://fapi.binance.com"
+SYMBOL = "XRPUSDT"
+DATA_DIR = Path("data/xrpusdt")
+FEE_RATE = 0.0004  # 0.04% per side
+
+
+async def fetch_oi_history(session, symbol, start_ms, end_ms):
+    """Binance Open Interest Statistics (15m) 수집"""
+    all_data = []
+    current = start_ms
+    calls = 0
+
+    while current < end_ms:
+        params = {
+            "symbol": symbol,
+            "period": "15m",
+            "startTime": current,
+            "endTime": end_ms,
+            "limit": 500,
+        }
+        async with session.get(f"{BASE}/futures/data/openInterestHist", params=params) as resp:
+            data = await resp.json()
+
+        if not data or not isinstance(data, list):
+            break
+
+        all_data.extend(data)
+        last_ts = int(data[-1]["timestamp"])
+        if last_ts <= current:
+            break
+        current = last_ts + 1
+        calls += 1
+
+        # Rate limit: ~10 weight per call, 1200/min limit
+        if calls % 50 == 0:
+            print(f"    ... {len(all_data)} rows fetched, sleeping 5s for rate limit")
+            await asyncio.sleep(5)
+        else:
+            await asyncio.sleep(0.1)
+
+    if not all_data:
+        return pd.DataFrame()
+
+    df = pd.DataFrame(all_data)
+    df["timestamp"] = pd.to_datetime(df["timestamp"].astype(int), unit="ms", utc=True)
+    df["sumOpenInterest"] = df["sumOpenInterest"].astype(float)
+    df["sumOpenInterestValue"] = df["sumOpenInterestValue"].astype(float)
+    return df[["timestamp", "sumOpenInterest", "sumOpenInterestValue"]].drop_duplicates("timestamp").sort_values("timestamp")
+
+
+async def fetch_funding_rate_history(session, symbol, start_ms, end_ms):
+    """Binance Funding Rate History 수집 (8시간 간격)"""
+    all_data = []
+    current = start_ms
+
+    while current < end_ms:
+        params = {
+            "symbol": symbol,
+            "startTime": current,
+            "endTime": end_ms,
+            "limit": 1000,
+        }
+        async with session.get(f"{BASE}/fapi/v1/fundingRate", params=params) as resp:
+            data = await resp.json()
+
+        if not data or not isinstance(data, list):
+            break
+
+        all_data.extend(data)
+        last_ts = int(data[-1]["fundingTime"])
+        if last_ts <= current:
+            break
+        current = last_ts + 1
+        await asyncio.sleep(0.1)
+
+    if not all_data:
+        return pd.DataFrame()
+
+    df = pd.DataFrame(all_data)
+    df["timestamp"] = pd.to_datetime(df["fundingTime"].astype(int), unit="ms", utc=True)
+    df["funding_rate_api"] = df["fundingRate"].astype(float)
+    return df[["timestamp", "funding_rate_api"]].drop_duplicates("timestamp").sort_values("timestamp")
+
+
+async def main():
+    print("=" * 80)
+    print("  Funding Rate + OI 변화율 상관분석")
+    print("=" * 80)
+
+    # Step 1: 데이터 수집
+    print("\n[Step 1] 데이터 수집")
+
+    # 기존 kline 로드
+    kline_path = DATA_DIR / "combined_15m.parquet"
+    df = pd.read_parquet(kline_path)
+    print(f"  기존 kline: {len(df)} rows ({df.index.min()} ~ {df.index.max()})")
+
+    # 기간 설정: OI는 30일 제한, FR은 무제한
+    end_dt = datetime.now(timezone.utc)
+    oi_start_dt = end_dt - timedelta(days=29)  # OI: 30일 제한
+    fr_start_dt = end_dt - timedelta(days=60)  # FR: 60일
+    kline_start_dt = fr_start_dt  # kline도 60일
+
+    # Clean timestamps (no microseconds)
+    oi_start_ms = int(oi_start_dt.replace(microsecond=0, second=0).timestamp()) * 1000
+    fr_start_ms = int(fr_start_dt.replace(microsecond=0, second=0).timestamp()) * 1000
+    end_ms = int(end_dt.replace(microsecond=0, second=0).timestamp()) * 1000
+
+    print(f"  OI 수집 기간: {oi_start_dt.date()} ~ {end_dt.date()} (29일)")
+    print(f"  FR 수집 기간: {fr_start_dt.date()} ~ {end_dt.date()} (60일)")
+
+    async with aiohttp.ClientSession() as session:
+        print("  OI 수집 중...")
+        oi_df = await fetch_oi_history(session, SYMBOL, oi_start_ms, end_ms)
+        print(f"  OI: {len(oi_df)} rows")
+
+        print("  Funding Rate 수집 중...")
+        fr_df = await fetch_funding_rate_history(session, SYMBOL, fr_start_ms, end_ms)
+        print(f"  Funding Rate: {len(fr_df)} rows")
+
+    # Step 2: 병합
+    print("\n[Step 2] 데이터 병합")
+
+    # 2개월 kline 슬라이스
+    df_2m = df.loc[kline_start_dt:].copy()
+    print(f"  2개월 kline: {len(df_2m)} rows")
+
+    # OI 병합 (merge_asof)
+    df_2m = df_2m.reset_index()
+    if not oi_df.empty:
+        df_2m = pd.merge_asof(
+            df_2m.sort_values("timestamp"),
+            oi_df.sort_values("timestamp"),
+            on="timestamp",
+            direction="nearest",
+            tolerance=pd.Timedelta(minutes=20),
+        )
+        # OI 변화율 계산
+        df_2m["oi"] = df_2m["sumOpenInterestValue"]
+        df_2m["oi_pct_change"] = df_2m["oi"].pct_change()
+        df_2m["oi_pct_change_4"] = df_2m["oi"].pct_change(4)  # 1시간 변화율
+        print(f"  OI 매칭: {df_2m['oi'].notna().sum()} rows")
+
+    # Funding Rate 병합 (8h → 15m forward fill)
+    if not fr_df.empty:
+        df_2m = pd.merge_asof(
+            df_2m.sort_values("timestamp"),
+            fr_df.sort_values("timestamp"),
+            on="timestamp",
+            direction="backward",  # 가장 최근 funding rate 사용
+        )
+        # Funding rate 변화율
+        df_2m["fr"] = df_2m["funding_rate_api"]
+        df_2m["fr_change"] = df_2m["fr"].diff()
+        print(f"  Funding Rate 매칭: {df_2m['fr'].notna().sum()} rows")
+
+    # 기존 funding_rate 컬럼도 활용
+    df_2m["fr_existing"] = df_2m["funding_rate"]
+    df_2m["fr_existing_change"] = df_2m["fr_existing"].diff()
+
+    # 미래 수익률 계산
+    df_2m["next_1h_return"] = df_2m["close"].shift(-4) / df_2m["close"] - 1
+    df_2m["next_4h_return"] = df_2m["close"].shift(-16) / df_2m["close"] - 1
+    df_2m["next_15m_return"] = df_2m["close"].shift(-1) / df_2m["close"] - 1
+
+    # 복합 피처
+    if "oi_pct_change" in df_2m.columns and "fr" in df_2m.columns:
+        df_2m["fr_x_oi"] = df_2m["fr"] * df_2m["oi_pct_change"]  # 펀딩비 × OI변화율
+        df_2m["fr_x_oi_4"] = df_2m["fr"] * df_2m["oi_pct_change_4"]
+
+    df_2m = df_2m.set_index("timestamp")
+
+    # OI velocity (변화율의 변화율)
+    if "oi_pct_change" in df_2m.columns:
+        df_2m["oi_velocity"] = df_2m["oi_pct_change"].diff()
+        df_2m["oi_acceleration"] = df_2m["oi_velocity"].diff()
+
+    print(f"\n  최종 데이터셋: {len(df_2m)} rows, {len(df_2m.columns)} columns")
+
+    # Step 3: 상관분석
+    print("\n[Step 3] 상관분석")
+    print("=" * 80)
+
+    features = [
+        ("fr_existing", "Funding Rate (기존)"),
+        ("fr_existing_change", "ΔFunding Rate"),
+        ("fr", "Funding Rate (API)"),
+        ("fr_change", "ΔFunding Rate (API)"),
+        ("oi_pct_change", "OI 변화율 (15m)"),
+        ("oi_pct_change_4", "OI 변화율 (1h)"),
+        ("oi_velocity", "OI Velocity"),
+        ("oi_acceleration", "OI Acceleration"),
+        ("fr_x_oi", "FR × OI변화율"),
+        ("fr_x_oi_4", "FR × OI변화율(1h)"),
+    ]
+
+    targets = [
+        ("next_15m_return", "다음 15m"),
+        ("next_1h_return", "다음 1h"),
+        ("next_4h_return", "다음 4h"),
+    ]
+
+    print(f"\n{'피처':<25} {'→15m':>8} {'→1h':>8} {'→4h':>8} {'N':>7}")
+    print("-" * 60)
+
+    strong_signals = []
+    for feat_col, feat_name in features:
+        if feat_col not in df_2m.columns:
+            continue
+        corrs = []
+        n = 0
+        for tgt_col, _ in targets:
+            valid = df_2m[[feat_col, tgt_col]].dropna()
+            n = len(valid)
+            if n > 50:
+                r = valid[feat_col].corr(valid[tgt_col])
+                corrs.append(r)
+            else:
+                corrs.append(float("nan"))
+
+        r_strs = [f"{r:>+8.4f}" if not np.isnan(r) else f"{'N/A':>8}" for r in corrs]
+        print(f"{feat_name:<25} {''.join(r_strs)} {n:>7}")
+
+        # 강한 시그널 체크 (|r| > 0.05)
+        for r, (tgt_col, tgt_name) in zip(corrs, targets):
+            if not np.isnan(r) and abs(r) > 0.05:
+                strong_signals.append((feat_name, tgt_name, r, n))
+
+    # Quintile 분석 (강한 시그널에 대해)
+    print("\n" + "=" * 80)
+    print("  [Quintile 분석] |r| > 0.05 피처")
+    print("=" * 80)
+
+    for feat_col, feat_name in features:
+        if feat_col not in df_2m.columns:
+            continue
+
+        for tgt_col, tgt_name in targets:
+            valid = df_2m[[feat_col, tgt_col]].dropna()
+            if len(valid) < 100:
+                continue
+            r = valid[feat_col].corr(valid[tgt_col])
+            if abs(r) < 0.05:
+                continue
+
+            print(f"\n  {feat_name} → {tgt_name} (r={r:+.4f}, n={len(valid)})")
+            print(f"  {'Quintile':<12} {'mean_feat':>12} {'return_bps':>12} {'win_rate':>10} {'count':>7}")
+            print("  " + "-" * 55)
+
+            try:
+                valid["q"] = pd.qcut(valid[feat_col], 5, labels=["Q1", "Q2", "Q3", "Q4", "Q5"], duplicates="drop")
+            except ValueError:
+                continue
+
+            for q in valid["q"].cat.categories:
+                grp = valid[valid["q"] == q]
+                if len(grp) == 0:
+                    continue
+                mr = grp[feat_col].mean()
+                ret = grp[tgt_col].mean() * 10000
+                wr = (grp[tgt_col] > 0).mean() * 100
+                print(f"  {q:<12} {mr:>12.6f} {ret:>+12.2f} {wr:>9.1f}% {len(grp):>7}")
+
+    # 판정
+    print("\n" + "=" * 80)
+    print("  [최종 판정]")
+    print("=" * 80)
+
+    if strong_signals:
+        print(f"\n  |r| > 0.05 시그널: {len(strong_signals)}개")
+        for feat, tgt, r, n in sorted(strong_signals, key=lambda x: abs(x[2]), reverse=True):
+            marker = "🟢" if abs(r) > 0.15 else "🟡" if abs(r) > 0.10 else "⚪"
+            print(f"  {marker} {feat} → {tgt}: r={r:+.4f} (n={n})")
+
+        best_r = max(abs(r) for _, _, r, _ in strong_signals)
+        if best_r > 0.15:
+            print(f"\n  ✅ r > 0.15 시그널 발견! 백테스트 진행 가치 있음")
+        elif best_r > 0.10:
+            print(f"\n  🟡 r = 0.10~0.15. L/S ratio(0.1158)과 비슷한 수준.")
+            print(f"     단, 2개월 데이터(8일 대비 7.5배)이므로 신뢰도 높음.")
+            print(f"     백테스트로 비용 후 PF 확인 필요.")
+        else:
+            print(f"\n  ⚠️ 최대 |r| = {best_r:.4f}. 약한 시그널.")
+            print(f"     비용(0.08%) 커버 가능성 낮음.")
+    else:
+        print("\n  🔴 |r| > 0.05 시그널 없음. Edge 없음.")
+
+    print("\n" + "=" * 80)
+    print("  분석 완료.")
+    print("=" * 80)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
--- a/scripts/ls_ratio_backtest.py
+++ b/scripts/ls_ratio_backtest.py
@@ -0,0 +1,485 @@
+"""
+L/S Ratio 단독 백테스트 — Phase 1: Pure Edge Test
+
+6개 조합 (3 임계값 × 2 방향) 스윕, 3단계 필터 판정.
+데이터: 프로덕션 수집 L/S ratio + Binance kline (같은 기간).
+
+Usage: python scripts/ls_ratio_backtest.py
+"""
+
+import asyncio
+import aiohttp
+import pandas as pd
+import numpy as np
+from datetime import timezone
+from pathlib import Path
+
+BASE = "https://fapi.binance.com"
+DATA_DIR = Path("data")
+SYMBOL = "XRPUSDT"
+FEE_RATE = 0.0004  # 0.04% per side
+HOLD_BARS = 4  # 4 candles = 1 hour
+
+
+async def fetch_klines(session, symbol, start_ms, end_ms):
+    """Binance kline 데이터 가져오기"""
+    all_klines = []
+    current = start_ms
+    while current < end_ms:
+        params = {
+            "symbol": symbol, "interval": "15m",
+            "startTime": current, "endTime": end_ms, "limit": 1500,
+        }
+        async with session.get(f"{BASE}/fapi/v1/klines", params=params) as resp:
+            data = await resp.json()
+        if not data:
+            break
+        all_klines.extend(data)
+        current = data[-1][0] + 1
+    return all_klines
+
+
+def load_ls_ratio(symbol):
+    """프로덕션 수집 L/S ratio 로드"""
+    path = DATA_DIR / symbol.lower() / "ls_ratio_15m.parquet"
+    if not path.exists():
+        raise FileNotFoundError(f"{path} not found. Sync from production first.")
+    df = pd.read_parquet(path)
+    df["timestamp"] = pd.to_datetime(df["timestamp"], utc=True)
+    return df.sort_values("timestamp").reset_index(drop=True)
+
+
+def build_dataset(klines_raw, ls_df):
+    """Kline + L/S ratio 조인"""
+    df = pd.DataFrame(klines_raw, columns=[
+        "open_time", "open", "high", "low", "close", "volume",
+        "close_time", "quote_vol", "trades", "taker_buy_vol",
+        "taker_buy_quote_vol", "ignore",
+    ])
+    df["timestamp"] = pd.to_datetime(df["open_time"], unit="ms", utc=True)
+    for c in ["open", "high", "low", "close", "volume"]:
+        df[c] = df[c].astype(float)
+
+    # L/S ratio 조인 (가장 가까운 타임스탬프)
+    df = df.sort_values("timestamp").reset_index(drop=True)
+    merged = pd.merge_asof(
+        df, ls_df, on="timestamp", direction="nearest",
+        tolerance=pd.Timedelta(minutes=20),
+    )
+    return merged
+
+
+def run_backtest(df, percentile, direction, hold_bars=HOLD_BARS):
+    """
+    단일 조합 백테스트 실행.
+
+    - percentile: L/S ratio 임계값 (0~100)
+    - direction: "LONG" or "SHORT"
+    - hold_bars: 보유 캔들 수
+
+    LONG 진입: ratio >= threshold (Momentum)
+    SHORT 진입: ratio <= threshold (Momentum)
+    """
+    threshold = df["top_acct_ls_ratio"].quantile(percentile / 100)
+
+    trades = []
+    i = 0
+    while i < len(df) - hold_bars:
+        ratio = df.iloc[i]["top_acct_ls_ratio"]
+        if pd.isna(ratio):
+            i += 1
+            continue
+
+        # 시그널 체크
+        if direction == "LONG" and ratio >= threshold:
+            entry_price = df.iloc[i + 1]["open"]  # 다음 캔들 시가 진입
+            exit_price = df.iloc[i + 1 + hold_bars - 1]["close"]  # hold_bars 후 종가
+            gross_return = (exit_price / entry_price) - 1
+            fee = FEE_RATE * 2  # 진입 + 청산
+            net_return = gross_return - fee
+            trades.append({
+                "entry_time": df.iloc[i + 1]["timestamp"],
+                "exit_time": df.iloc[i + 1 + hold_bars - 1]["timestamp"],
+                "entry_price": entry_price,
+                "exit_price": exit_price,
+                "entry_ls_ratio": ratio,
+                "gross_return_bps": gross_return * 10000,
+                "net_return_bps": net_return * 10000,
+                "fee_bps": fee * 10000,
+            })
+            i += 1 + hold_bars  # 포지션 종료 후 다음 캔들부터
+        elif direction == "SHORT" and ratio <= threshold:
+            entry_price = df.iloc[i + 1]["open"]
+            exit_price = df.iloc[i + 1 + hold_bars - 1]["close"]
+            gross_return = (entry_price / exit_price) - 1  # SHORT: 반대
+            fee = FEE_RATE * 2
+            net_return = gross_return - fee
+            trades.append({
+                "entry_time": df.iloc[i + 1]["timestamp"],
+                "exit_time": df.iloc[i + 1 + hold_bars - 1]["timestamp"],
+                "entry_price": entry_price,
+                "exit_price": exit_price,
+                "entry_ls_ratio": ratio,
+                "gross_return_bps": gross_return * 10000,
+                "net_return_bps": net_return * 10000,
+                "fee_bps": fee * 10000,
+            })
+            i += 1 + hold_bars
+        else:
+            i += 1
+
+    if not trades:
+        return None
+
+    df_trades = pd.DataFrame(trades)
+
+    # PF 계산: Σ(net profit) / Σ(|net loss|)
+    wins = df_trades[df_trades["net_return_bps"] > 0]["net_return_bps"]
+    losses = df_trades[df_trades["net_return_bps"] <= 0]["net_return_bps"]
+
+    gross_profit = wins.sum() if len(wins) > 0 else 0
+    gross_loss = abs(losses.sum()) if len(losses) > 0 else 0
+
+    pf = gross_profit / gross_loss if gross_loss > 0 else float("inf") if gross_profit > 0 else 0
+
+    # Max Drawdown (cumulative bps)
+    cum_pnl = df_trades["net_return_bps"].cumsum()
+    running_max = cum_pnl.cummax()
+    drawdown = cum_pnl - running_max
+    max_dd = drawdown.min()
+
+    return {
+        "trades": len(df_trades),
+        "wins": len(wins),
+        "losses": len(losses),
+        "win_rate": len(wins) / len(df_trades) * 100,
+        "pf": pf,
+        "total_pnl_bps": df_trades["net_return_bps"].sum(),
+        "avg_pnl_bps": df_trades["net_return_bps"].mean(),
+        "max_dd_bps": max_dd,
+        "threshold": threshold,
+        "df_trades": df_trades,
+    }
+
+
+def confidence_emoji(n_trades):
+    if n_trades < 20:
+        return "🔴"
+    elif n_trades < 50:
+        return "🟡"
+    elif n_trades < 100:
+        return "🟢"
+    else:
+        return "🟢"
+
+
+def confidence_label(n_trades):
+    if n_trades < 20:
+        return "폐기(과적합)"
+    elif n_trades < 50:
+        return "낮음(참고만)"
+    elif n_trades < 100:
+        return "보통(검토)"
+    else:
+        return "높음(우선)"
+
+
+async def main():
+    print("=" * 80)
+    print("  L/S Ratio 단독 백테스트 — Phase 1: Pure Edge Test")
+    print("=" * 80)
+
+    # 1. 데이터 로드
+    print("\n[1] 데이터 로드")
+    ls_df = load_ls_ratio(SYMBOL)
+    print(f"  L/S ratio: {len(ls_df)} rows ({ls_df['timestamp'].min()} ~ {ls_df['timestamp'].max()})")
+
+    start_ms = int(ls_df["timestamp"].min().timestamp() * 1000)
+    end_ms = int(ls_df["timestamp"].max().timestamp() * 1000)
+
+    async with aiohttp.ClientSession() as session:
+        klines = await fetch_klines(session, SYMBOL, start_ms, end_ms)
+    print(f"  Klines: {len(klines)} rows")
+
+    df = build_dataset(klines, ls_df)
+    valid = df.dropna(subset=["top_acct_ls_ratio"])
+    print(f"  조인 결과: {len(df)} rows (L/S 매칭: {len(valid)})")
+    print(f"  top_acct_ls_ratio: mean={valid['top_acct_ls_ratio'].mean():.4f}, "
+          f"std={valid['top_acct_ls_ratio'].std():.4f}")
+
+    # 백분위수 표시
+    for p in [25, 50, 75]:
+        v = valid["top_acct_ls_ratio"].quantile(p / 100)
+        print(f"  P{p}: {v:.4f}")
+
+    # 2. 6개 조합 백테스트
+    print("\n[2] 6개 조합 백테스트 실행")
+    print("-" * 80)
+
+    combinations = [
+        (75, "LONG", "모멘텀 강함: ratio ≥ P75 → LONG"),
+        (75, "SHORT", "역모멘텀: ratio ≥ P75 → SHORT"),
+        (50, "LONG", "모멘텀 중간: ratio ≥ P50 → LONG"),
+        (50, "SHORT", "역모멘텀 중간: ratio ≤ P50 → SHORT"),
+        (25, "LONG", "역모멘텀 약: ratio ≤ P25 → LONG"),
+        (25, "SHORT", "모멘텀 강함: ratio ≤ P25 → SHORT"),
+    ]
+
+    results = []
+    for pct, direction, desc in combinations:
+        # LONG: ratio >= threshold, SHORT: ratio <= threshold
+        # 25th percentile LONG = ratio가 낮을 때 LONG (Contrarian)
+        # 실제 로직:
+        #   75 LONG = ratio >= P75 (상위 25% 롱비율 높을 때 롱) = Momentum
+        #   75 SHORT = ratio >= P75 (상위 25% 롱비율 높을 때 숏) = Contrarian
+        #   25 SHORT = ratio <= P25 (하위 25% 롱비율 낮을 때 숏) = Momentum
+        #   25 LONG = ratio <= P25 (하위 25% 롱비율 낮을 때 롱) = Contrarian
+
+        # 방향 보정: 25th에서 LONG은 "ratio <= P25일 때 LONG" (Contrarian)
+        if pct == 25 and direction == "LONG":
+            # 특수 케이스: 낮은 ratio에서 LONG (Contrarian)
+            result = run_backtest_contrarian(df, pct, "LONG")
+        elif pct == 25 and direction == "SHORT":
+            # ratio <= P25일 때 SHORT (Momentum)
+            result = run_backtest(df, pct, "SHORT")
+        elif pct == 75 and direction == "SHORT":
+            # ratio >= P75일 때 SHORT (Contrarian)
+            result = run_backtest_contrarian(df, pct, "SHORT")
+        else:
+            result = run_backtest(df, pct, direction)
+
+        if result:
+            result["percentile"] = pct
+            result["direction"] = direction
+            result["description"] = desc
+            results.append(result)
+        else:
+            results.append({
+                "percentile": pct, "direction": direction,
+                "description": desc, "trades": 0, "pf": 0,
+                "win_rate": 0, "total_pnl_bps": 0, "max_dd_bps": 0,
+                "threshold": 0, "wins": 0, "losses": 0, "avg_pnl_bps": 0,
+            })
+
+    # 3. 결과 테이블
+    print("\n[3] 결과 테이블")
+    print("=" * 80)
+    print(f"{'조합':<35} {'거래수':>6} {'승률':>7} {'PF':>7} {'PnL(bps)':>10} {'MaxDD':>10} {'신뢰도':<15}")
+    print("-" * 80)
+
+    for r in results:
+        emoji = confidence_emoji(r["trades"])
+        label = confidence_label(r["trades"])
+        pf_str = f"{r['pf']:.2f}" if r["pf"] != float("inf") else "INF"
+        print(f"{r['description']:<35} {r['trades']:>6} {r['win_rate']:>6.1f}% {pf_str:>7} "
+              f"{r['total_pnl_bps']:>+10.1f} {r['max_dd_bps']:>10.1f} {emoji} {label}")
+
+    # 4. 필터 1: PF 판정
+    print("\n[4] 필터 1: PF 판정")
+    print("-" * 80)
+
+    strong = [r for r in results if r["pf"] > 1.5 and r["trades"] > 0]
+    weak = [r for r in results if 0.5 <= r["pf"] <= 1.5 and r["trades"] > 0]
+    failed = [r for r in results if r["pf"] < 0.5 and r["trades"] > 0]
+
+    print(f"  PF > 1.5 (명확한 edge):  {len(strong)}개 조합")
+    for r in strong:
+        print(f"    → {r['description']} (PF={r['pf']:.2f}, trades={r['trades']})")
+    print(f"  0.5 ≤ PF ≤ 1.5 (보류): {len(weak)}개 조합")
+    for r in weak:
+        print(f"    ~ {r['description']} (PF={r['pf']:.2f}, trades={r['trades']})")
+    print(f"  PF < 0.5 (실패):        {len(failed)}개 조합")
+    for r in failed:
+        print(f"    ✗ {r['description']} (PF={r['pf']:.2f}, trades={r['trades']})")
+
+    # 5. 필터 2: 거래수 신뢰도
+    print("\n[5] 필터 2: 거래수 신뢰도 (필터 1 통과 조합)")
+    print("-" * 80)
+
+    filter2_passed = [r for r in strong if r["trades"] >= 20]
+    filter2_ref = [r for r in strong if r["trades"] < 20]
+
+    if filter2_passed:
+        for r in filter2_passed:
+            print(f"  ✓ {r['description']} — {r['trades']}건 ({confidence_label(r['trades'])})")
+    else:
+        print("  ⚠️ PF > 1.5 조합 중 거래수 20건 이상인 것 없음")
+    if filter2_ref:
+        for r in filter2_ref:
+            print(f"  🔴 {r['description']} — {r['trades']}건 (폐기: 과적합)")
+
+    # 6. 필터 3: 대칭성 판정
+    print("\n[6] 필터 3: 대칭성 판정")
+    print("-" * 80)
+
+    # 같은 percentile에서 LONG/SHORT 양쪽 확인
+    for pct in [75, 50, 25]:
+        long_r = next((r for r in results if r["percentile"] == pct and r["direction"] == "LONG"), None)
+        short_r = next((r for r in results if r["percentile"] == pct and r["direction"] == "SHORT"), None)
+        if not long_r or not short_r:
+            continue
+
+        l_pf = long_r["pf"]
+        s_pf = short_r["pf"]
+
+        if l_pf > 1.5 and s_pf > 1.5:
+            verdict = "Case 1: 양방향 생존 → ✓ Phase 2 후보"
+        elif (l_pf > 1.5 and s_pf < 0.5) or (s_pf > 1.5 and l_pf < 0.5):
+            verdict = "Case 2: 한쪽만 성공 → ✗ 시장 베타/우연 (폐기)"
+        elif l_pf > 1.5 or s_pf > 1.5:
+            verdict = "Case 3: 부분적 edge → ~ 낮은 신뢰도"
+        else:
+            verdict = "양쪽 모두 약함 → 해당 없음"
+
+        print(f"  P{pct}: LONG PF={l_pf:.2f}, SHORT PF={s_pf:.2f}")
+        print(f"       → {verdict}")
+
+    # 7. 최종 판정
+    print("\n" + "=" * 80)
+    print("  [최종 판정]")
+    print("=" * 80)
+
+    # Phase 2 후보 찾기
+    phase2_candidates = []
+    for pct in [75, 50, 25]:
+        long_r = next((r for r in results if r["percentile"] == pct and r["direction"] == "LONG"), None)
+        short_r = next((r for r in results if r["percentile"] == pct and r["direction"] == "SHORT"), None)
+        if not long_r or not short_r:
+            continue
+
+        # Case 1: 양방향 PF > 1.5
+        if long_r["pf"] > 1.5 and short_r["pf"] > 1.5:
+            if long_r["trades"] >= 20 and short_r["trades"] >= 20:
+                phase2_candidates.append(("Case1", pct, long_r, short_r))
+        # Case 3: 한쪽만 PF > 1.5
+        elif long_r["pf"] > 1.5 and long_r["trades"] >= 20:
+            phase2_candidates.append(("Case3-LONG", pct, long_r, short_r))
+        elif short_r["pf"] > 1.5 and short_r["trades"] >= 20:
+            phase2_candidates.append(("Case3-SHORT", pct, long_r, short_r))
+
+    if phase2_candidates:
+        print("\n  🟢 Phase 2 진행 후보 발견!")
+        for case, pct, lr, sr in phase2_candidates:
+            print(f"    [{case}] P{pct}: LONG PF={lr['pf']:.2f}({lr['trades']}건), "
+                  f"SHORT PF={sr['pf']:.2f}({sr['trades']}건)")
+        print("\n  → Phase 2 (Bot Simulation) 진행 권장")
+        print("  → 단, 8일 데이터이므로 4월 15일 재검증 필수")
+    else:
+        # 모든 조합 중 최고 PF
+        best = max(results, key=lambda r: r["pf"] if r["trades"] > 0 else 0)
+        if best["pf"] > 1.0:
+            print(f"\n  🟡 필터 미통과이나 PF > 1.0 조합 존재")
+            print(f"    Best: {best['description']} (PF={best['pf']:.2f}, {best['trades']}건)")
+            print(f"\n  → 데이터 부족. 4월 15일까지 수집 후 재검증")
+        else:
+            print(f"\n  🔴 PF > 1.0 조합 없음")
+            print(f"    Best: {best['description']} (PF={best['pf']:.2f}, {best['trades']}건)")
+            print(f"\n  → L/S ratio 단독 시그널로는 edge 없음")
+            print(f"  → 다른 데이터 소스 탐색 권장")
+
+    # 8. 추가: 전 구간 상세 (best 조합)
+    best = max(results, key=lambda r: r["pf"] if r["trades"] > 10 else 0)
+    if "df_trades" in best and best["trades"] > 0:
+        print(f"\n[참고] Best 조합 상세: {best['description']}")
+        print("-" * 60)
+        tdf = best["df_trades"]
+        print(f"  거래 기간: {tdf['entry_time'].min()} ~ {tdf['exit_time'].max()}")
+        print(f"  평균 진입 L/S ratio: {tdf['entry_ls_ratio'].mean():.4f}")
+        print(f"  수익 거래 평균: {tdf[tdf['net_return_bps']>0]['net_return_bps'].mean():.1f} bps")
+        if len(tdf[tdf['net_return_bps'] <= 0]) > 0:
+            print(f"  손실 거래 평균: {tdf[tdf['net_return_bps']<=0]['net_return_bps'].mean():.1f} bps")
+        print(f"  최대 연승: ", end="")
+        streaks = []
+        streak = 0
+        for _, row in tdf.iterrows():
+            if row["net_return_bps"] > 0:
+                streak += 1
+            else:
+                if streak > 0:
+                    streaks.append(streak)
+                streak = 0
+        if streak > 0:
+            streaks.append(streak)
+        print(f"{max(streaks) if streaks else 0}연승")
+
+    print("\n" + "=" * 80)
+    print("  분석 완료. 결과를 바탕으로 의사결정하세요.")
+    print("=" * 80)
+
+
+def run_backtest_contrarian(df, percentile, direction, hold_bars=HOLD_BARS):
+    """
+    Contrarian 방향 백테스트.
+    - P25 + LONG: ratio <= P25일 때 LONG (낮은 ratio에서 롱)
+    - P75 + SHORT: ratio >= P75일 때 SHORT (높은 ratio에서 숏)
+    """
+    threshold = df["top_acct_ls_ratio"].quantile(percentile / 100)
+
+    trades = []
+    i = 0
+    while i < len(df) - hold_bars:
+        ratio = df.iloc[i]["top_acct_ls_ratio"]
+        if pd.isna(ratio):
+            i += 1
+            continue
+
+        trigger = False
+        if direction == "LONG" and ratio <= threshold:
+            trigger = True
+        elif direction == "SHORT" and ratio >= threshold:
+            trigger = True
+
+        if trigger:
+            entry_price = df.iloc[i + 1]["open"]
+            exit_price = df.iloc[i + 1 + hold_bars - 1]["close"]
+            if direction == "LONG":
+                gross_return = (exit_price / entry_price) - 1
+            else:
+                gross_return = (entry_price / exit_price) - 1
+            fee = FEE_RATE * 2
+            net_return = gross_return - fee
+            trades.append({
+                "entry_time": df.iloc[i + 1]["timestamp"],
+                "exit_time": df.iloc[i + 1 + hold_bars - 1]["timestamp"],
+                "entry_price": entry_price,
+                "exit_price": exit_price,
+                "entry_ls_ratio": ratio,
+                "gross_return_bps": gross_return * 10000,
+                "net_return_bps": net_return * 10000,
+                "fee_bps": fee * 10000,
+            })
+            i += 1 + hold_bars
+        else:
+            i += 1
+
+    if not trades:
+        return None
+
+    df_trades = pd.DataFrame(trades)
+    wins = df_trades[df_trades["net_return_bps"] > 0]["net_return_bps"]
+    losses = df_trades[df_trades["net_return_bps"] <= 0]["net_return_bps"]
+
+    gross_profit = wins.sum() if len(wins) > 0 else 0
+    gross_loss = abs(losses.sum()) if len(losses) > 0 else 0
+    pf = gross_profit / gross_loss if gross_loss > 0 else float("inf") if gross_profit > 0 else 0
+
+    cum_pnl = df_trades["net_return_bps"].cumsum()
+    running_max = cum_pnl.cummax()
+    max_dd = (cum_pnl - running_max).min()
+
+    return {
+        "trades": len(df_trades),
+        "wins": len(wins),
+        "losses": len(losses),
+        "win_rate": len(wins) / len(df_trades) * 100,
+        "pf": pf,
+        "total_pnl_bps": df_trades["net_return_bps"].sum(),
+        "avg_pnl_bps": df_trades["net_return_bps"].mean(),
+        "max_dd_bps": max_dd,
+        "threshold": threshold,
+        "df_trades": df_trades,
+    }
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
--- a/scripts/mtf_btc_filter_backtest.py
+++ b/scripts/mtf_btc_filter_backtest.py
@@ -0,0 +1,601 @@
+"""
+MTF Pullback + BTC 추세 필터 백테스트
+──────────────────────────────────────
+기존 MTF Pullback 전략에 BTC 추세 필터를 추가하여 검증.
+
+메인 가설 (사전 확정):
+  BTC 1h + EMA 50/200 + ADX > 20
+  sweep 결과와 무관하게 사후 변경하지 않음.
+
+판정 흐름:
+  1. 베이스라인(필터 없음) IS/OOS 결과 산출
+  2. 12개 sweep IS, 메인 가설 OOS 검증
+  3. 나머지 11개 OOS robustness 체크
+
+Usage:
+    python scripts/mtf_btc_filter_backtest.py
+    python scripts/mtf_btc_filter_backtest.py --symbol xrpusdt
+"""
+
+import sys
+from pathlib import Path
+from dataclasses import dataclass, field
+from itertools import product
+
+import pandas as pd
+import pandas_ta as ta
+import numpy as np
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+from src.config import COST_MODEL, COST_SCENARIOS  # noqa: E402
+
+# ─── 설정 ──────────────────────────────────────────────────────────
+SYMBOL = "xrpusdt"
+DATA_PATH = Path(f"data/{SYMBOL}/combined_15m.parquet")
+
+# XRP 1h 메타필터 (기존 MTF bot 설정 그대로)
+MTF_EMA_FAST = 50
+MTF_EMA_SLOW = 200
+MTF_ADX_THRESHOLD = 20
+
+# 15m Trigger
+EMA_PULLBACK_LEN = 20
+VOL_DRY_RATIO = 0.5
+
+# SL/TP
+ATR_SL_MULT = 1.5
+ATR_TP_MULT = 2.3
+
+# IS/OOS 분할
+IS_RATIO = 0.7
+
+# ─── Sweep 그리드 ─────────────────────────────────────────────────
+SWEEP_GRID = {
+    "btc_tf": ["1h", "4h", "1D"],
+    "btc_ema_fast": [20, 50],
+    "btc_ema_slow": [100, 200],
+}
+
+# BTC ADX 임계값 — 전 조합 고정
+BTC_ADX_THRESHOLD = 20
+
+# 메인 가설 (사전 확정 — commitment device)
+MAIN_HYPOTHESIS = {"btc_tf": "1h", "btc_ema_fast": 50, "btc_ema_slow": 200}
+
+# IS 거래 수 최소 기준
+MIN_IS_TRADES = 100
+
+
+@dataclass
+class Trade:
+    entry_time: pd.Timestamp
+    entry_price: float
+    side: str
+    sl: float
+    tp: float
+    btc_trend: str = ""
+    exit_time: pd.Timestamp | None = None
+    exit_price: float | None = None
+    pnl_bps: float | None = None
+    reason: str = ""
+
+
+def build_xrp_1h(df_15m: pd.DataFrame) -> pd.DataFrame:
+    """XRP 15m → 1h: EMA50, EMA200, ADX, ATR."""
+    df_1h = df_15m[["open", "high", "low", "close", "volume"]].resample("1h").agg(
+        {"open": "first", "high": "max", "low": "min", "close": "last", "volume": "sum"}
+    ).dropna()
+
+    df_1h["ema50_1h"] = ta.ema(df_1h["close"], length=MTF_EMA_FAST)
+    df_1h["ema200_1h"] = ta.ema(df_1h["close"], length=MTF_EMA_SLOW)
+    adx_df = ta.adx(df_1h["high"], df_1h["low"], df_1h["close"], length=14)
+    df_1h["adx_1h"] = adx_df["ADX_14"]
+    df_1h["atr_1h"] = ta.atr(df_1h["high"], df_1h["low"], df_1h["close"], length=14)
+
+    return df_1h[["ema50_1h", "ema200_1h", "adx_1h", "atr_1h"]]
+
+
+def build_btc_resampled(df_15m: pd.DataFrame, tf: str, ema_fast: int, ema_slow: int) -> pd.DataFrame:
+    """BTC 15m → 지정 타임프레임: EMA + ADX."""
+    btc_cols = {"open_btc": "open", "high_btc": "high", "low_btc": "low",
+                "close_btc": "close", "volume_btc": "volume"}
+    df_btc = df_15m[list(btc_cols.keys())].rename(columns=btc_cols)
+
+    df_rs = df_btc.resample(tf).agg(
+        {"open": "first", "high": "max", "low": "min", "close": "last", "volume": "sum"}
+    ).dropna()
+
+    df_rs[f"btc_ema_fast"] = ta.ema(df_rs["close"], length=ema_fast)
+    df_rs[f"btc_ema_slow"] = ta.ema(df_rs["close"], length=ema_slow)
+    adx_df = ta.adx(df_rs["high"], df_rs["low"], df_rs["close"], length=14)
+    df_rs["btc_adx"] = adx_df["ADX_14"]
+
+    return df_rs[["btc_ema_fast", "btc_ema_slow", "btc_adx"]]
+
+
+def merge_higher_tf(df_15m: pd.DataFrame, df_htf: pd.DataFrame, tf: str) -> pd.DataFrame:
+    """Look-ahead bias 방지 merge. 1h → +1h shift, 4h → +4h shift, 1d → +1d shift."""
+    shift_map = {"1h": pd.Timedelta(hours=1), "4h": pd.Timedelta(hours=4),
+                 "1D": pd.Timedelta(days=1)}
+    df_shifted = df_htf.copy()
+    df_shifted.index = df_shifted.index + shift_map[tf]
+
+    df_15m_r = df_15m.reset_index()
+    df_htf_r = df_shifted.reset_index()
+    ts_col_15m = df_15m_r.columns[0]
+    ts_col_htf = df_htf_r.columns[0]
+    df_15m_r.rename(columns={ts_col_15m: "timestamp"}, inplace=True)
+    df_htf_r.rename(columns={ts_col_htf: "timestamp"}, inplace=True)
+
+    df_15m_r["timestamp"] = pd.to_datetime(df_15m_r["timestamp"]).astype("datetime64[us]")
+    df_htf_r["timestamp"] = pd.to_datetime(df_htf_r["timestamp"]).astype("datetime64[us]")
+
+    merged = pd.merge_asof(
+        df_15m_r.sort_values("timestamp"),
+        df_htf_r.sort_values("timestamp"),
+        on="timestamp",
+        direction="backward",
+    )
+    return merged.set_index("timestamp")
+
+
+def get_xrp_meta(row) -> str:
+    """XRP 1h 메타필터."""
+    ema50 = row.get("ema50_1h")
+    ema200 = row.get("ema200_1h")
+    adx = row.get("adx_1h")
+    if pd.isna(ema50) or pd.isna(ema200) or pd.isna(adx):
+        return "HOLD"
+    if adx < MTF_ADX_THRESHOLD:
+        return "HOLD"
+    return "LONG" if ema50 > ema200 else "SHORT"
+
+
+def get_btc_trend(row) -> str:
+    """BTC 추세 필터."""
+    ema_f = row.get("btc_ema_fast")
+    ema_s = row.get("btc_ema_slow")
+    adx = row.get("btc_adx")
+    if pd.isna(ema_f) or pd.isna(ema_s) or pd.isna(adx):
+        return "NEUTRAL"
+    if adx < BTC_ADX_THRESHOLD:
+        return "NEUTRAL"
+    return "UP" if ema_f > ema_s else "DOWN"
+
+
+def run_backtest(df: pd.DataFrame, use_btc_filter: bool) -> list[Trade]:
+    """MTF Pullback 백테스트 실행."""
+    trades: list[Trade] = []
+    in_trade = False
+    current_trade: Trade | None = None
+    pullback_ready = False
+    pullback_side = ""
+
+    for i in range(1, len(df)):
+        row = df.iloc[i]
+
+        # ── SL/TP 체크 ──
+        if in_trade and current_trade is not None:
+            hit_sl = hit_tp = False
+            if current_trade.side == "LONG":
+                hit_sl = row["low"] <= current_trade.sl
+                hit_tp = row["high"] >= current_trade.tp
+            else:
+                hit_sl = row["high"] >= current_trade.sl
+                hit_tp = row["low"] <= current_trade.tp
+
+            if hit_sl or hit_tp:
+                exit_price = current_trade.sl if hit_sl else current_trade.tp
+                if hit_sl and hit_tp:
+                    exit_price = current_trade.sl  # 보수적
+
+                if current_trade.side == "LONG":
+                    raw_pnl = (exit_price - current_trade.entry_price) / current_trade.entry_price
+                else:
+                    raw_pnl = (current_trade.entry_price - exit_price) / current_trade.entry_price
+
+                current_trade.exit_time = df.index[i]
+                current_trade.exit_price = exit_price
+                current_trade.pnl_bps = raw_pnl * 10000  # raw bps (비용 미반영)
+                current_trade.reason = "SL" if hit_sl else "TP"
+                trades.append(current_trade)
+                in_trade = False
+                current_trade = None
+
+        if in_trade:
+            continue
+
+        # NaN 체크
+        if pd.isna(row.get("ema20")) or pd.isna(row.get("vol_ma20")) or pd.isna(row.get("atr_1h")):
+            pullback_ready = False
+            continue
+
+        # ── XRP 1h Meta ──
+        meta = get_xrp_meta(row)
+        if meta == "HOLD":
+            pullback_ready = False
+            continue
+
+        # ── BTC 추세 필터 ──
+        btc_trend = get_btc_trend(row) if use_btc_filter else "DISABLED"
+
+        if use_btc_filter:
+            # BTC UP → LONG만, BTC DOWN → SHORT만, NEUTRAL → 차단
+            if btc_trend == "UP" and meta != "LONG":
+                pullback_ready = False
+                continue
+            elif btc_trend == "DOWN" and meta != "SHORT":
+                pullback_ready = False
+                continue
+            elif btc_trend == "NEUTRAL":
+                pullback_ready = False
+                continue
+
+        # ── Pullback 감지 → 재개 확인 ──
+        if pullback_ready and pullback_side == meta:
+            if pullback_side == "LONG" and row["close"] > row["ema20"]:
+                if i + 1 < len(df):
+                    next_row = df.iloc[i + 1]
+                    entry_price = next_row["open"]
+                    atr = row["atr_1h"]
+                    current_trade = Trade(
+                        entry_time=df.index[i + 1], entry_price=entry_price,
+                        side="LONG", sl=entry_price - atr * ATR_SL_MULT,
+                        tp=entry_price + atr * ATR_TP_MULT, btc_trend=btc_trend,
+                    )
+                    in_trade = True
+                    pullback_ready = False
+                    continue
+
+            elif pullback_side == "SHORT" and row["close"] < row["ema20"]:
+                if i + 1 < len(df):
+                    next_row = df.iloc[i + 1]
+                    entry_price = next_row["open"]
+                    atr = row["atr_1h"]
+                    current_trade = Trade(
+                        entry_time=df.index[i + 1], entry_price=entry_price,
+                        side="SHORT", sl=entry_price + atr * ATR_SL_MULT,
+                        tp=entry_price - atr * ATR_TP_MULT, btc_trend=btc_trend,
+                    )
+                    in_trade = True
+                    pullback_ready = False
+                    continue
+
+        # ── Pullback 감지 ──
+        vol_dry = row["volume"] < row["vol_ma20"] * VOL_DRY_RATIO
+        if meta == "LONG" and row["close"] < row["ema20"] and vol_dry:
+            pullback_ready = True
+            pullback_side = "LONG"
+        elif meta == "SHORT" and row["close"] > row["ema20"] and vol_dry:
+            pullback_ready = True
+            pullback_side = "SHORT"
+        elif meta != pullback_side:
+            pullback_ready = False
+
+    return trades
+
+
+def apply_cost(trades: list[Trade], scenario_name: str) -> list[float]:
+    """거래 리스트에 비용 시나리오 적용, adjusted pnl_bps 리스트 반환."""
+    scenario = COST_SCENARIOS[scenario_name]
+    fee_per_side = COST_MODEL["taker_fee_bps"]  # 현재 전부 taker
+    fee_roundtrip = fee_per_side * 2
+    slippage_roundtrip = scenario["slippage_bps_per_side"] * 2
+
+    adjusted = []
+    for t in trades:
+        # 펀딩비: 보유 시간 중 8h 경계 교차 수
+        if t.entry_time is not None and t.exit_time is not None:
+            dur_h = (t.exit_time - t.entry_time).total_seconds() / 3600
+            funding_events = max(0, int(dur_h / 8))
+        else:
+            funding_events = 0
+        funding_cost = funding_events * scenario["funding_bps_per_8h"]
+        total_cost = fee_roundtrip + slippage_roundtrip + funding_cost
+        adjusted.append(t.pnl_bps - total_cost)
+    return adjusted
+
+
+def calc_metrics(pnl_list: list[float]) -> dict:
+    """pnl_bps 리스트로 메트릭 계산."""
+    if not pnl_list:
+        return {"trades": 0, "win_rate": 0.0, "pf": 0.0, "cum_pnl": 0.0, "avg_pnl": 0.0}
+
+    wins = [p for p in pnl_list if p > 0]
+    losses = [p for p in pnl_list if p <= 0]
+    gross_profit = sum(wins) if wins else 0
+    gross_loss = abs(sum(losses)) if losses else 0
+    pf = gross_profit / gross_loss if gross_loss > 0 else float("inf")
+
+    return {
+        "trades": len(pnl_list),
+        "win_rate": round(len(wins) / len(pnl_list) * 100, 1),
+        "pf": round(pf, 2),
+        "cum_pnl": round(sum(pnl_list), 1),
+        "avg_pnl": round(sum(pnl_list) / len(pnl_list), 2),
+    }
+
+
+def split_is_oos(trades: list[Trade], split_ts: pd.Timestamp):
+    """IS/OOS 분할."""
+    is_trades = [t for t in trades if t.entry_time < split_ts]
+    oos_trades = [t for t in trades if t.entry_time >= split_ts]
+    return is_trades, oos_trades
+
+
+def print_metrics_row(label: str, raw: dict, fees: dict, realistic: dict):
+    """한 줄 메트릭 출력."""
+    print(f"  {label:<8} {raw['trades']:>5}  {raw['win_rate']:>5.1f}%  "
+          f"{raw['pf']:>5.2f}  {fees['pf']:>5.2f}  {realistic['pf']:>5.2f}  "
+          f"{raw['cum_pnl']:>+8.1f}  {fees['cum_pnl']:>+8.1f}")
+
+
+def print_section(title: str, trades: list[Trade]):
+    """섹션별 메트릭 출력."""
+    if not trades:
+        print(f"\n  [{title}] 거래 없음")
+        return
+
+    raw_all = [t.pnl_bps for t in trades]
+    fees_all = apply_cost(trades, "fees_only")
+    real_all = apply_cost(trades, "realistic")
+
+    long_t = [t for t in trades if t.side == "LONG"]
+    short_t = [t for t in trades if t.side == "SHORT"]
+
+    raw_l = [t.pnl_bps for t in long_t]
+    raw_s = [t.pnl_bps for t in short_t]
+    fees_l = apply_cost(long_t, "fees_only")
+    fees_s = apply_cost(short_t, "fees_only")
+    real_l = apply_cost(long_t, "realistic")
+    real_s = apply_cost(short_t, "realistic")
+
+    print(f"\n  [{title}]")
+    print(f"  {'':8} {'N':>5}  {'WR':>6}  {'RawPF':>5}  {'FeePF':>5}  {'RealPF':>5}  {'RawPnL':>8}  {'FeePnL':>8}")
+    print(f"  {'-'*62}")
+    print_metrics_row("Total", calc_metrics(raw_all), calc_metrics(fees_all), calc_metrics(real_all))
+    print_metrics_row("LONG", calc_metrics(raw_l), calc_metrics(fees_l), calc_metrics(real_l))
+    print_metrics_row("SHORT", calc_metrics(raw_s), calc_metrics(fees_s), calc_metrics(real_s))
+
+
+def save_trade_log(trades: list[Trade], filepath: Path, combo_label: str):
+    """거래 수준 CSV 로그 저장."""
+    rows = []
+    for t in trades:
+        rows.append({
+            "combo": combo_label,
+            "entry_time": t.entry_time,
+            "exit_time": t.exit_time,
+            "side": t.side,
+            "entry_price": t.entry_price,
+            "exit_price": t.exit_price,
+            "pnl_bps": t.pnl_bps,
+            "reason": t.reason,
+            "btc_trend": t.btc_trend,
+        })
+    df = pd.DataFrame(rows)
+    mode = "a" if filepath.exists() else "w"
+    header = not filepath.exists()
+    df.to_csv(filepath, mode=mode, header=header, index=False)
+
+
+def main():
+    import argparse
+    parser = argparse.ArgumentParser(description="MTF + BTC 추세 필터 백테스트")
+    parser.add_argument("--symbol", default="xrpusdt")
+    args = parser.parse_args()
+
+    data_path = Path(f"data/{args.symbol}/combined_15m.parquet")
+    print("=" * 72)
+    print("  MTF Pullback + BTC 추세 필터 백테스트")
+    print(f"  메인 가설: BTC {MAIN_HYPOTHESIS['btc_tf']} EMA{MAIN_HYPOTHESIS['btc_ema_fast']}/{MAIN_HYPOTHESIS['btc_ema_slow']} ADX>{BTC_ADX_THRESHOLD}")
+    print("=" * 72)
+
+    # ── 데이터 로드 ──
+    df_raw = pd.read_parquet(data_path)
+    if df_raw.index.tz is not None:
+        df_raw.index = df_raw.index.tz_localize(None)
+
+    # EMA200 워밍업 (200h × 4 + 여유 = 1000 bars)
+    warmup_bars = 1000
+    df_full = df_raw.iloc[warmup_bars:].copy() if len(df_raw) > warmup_bars else df_raw.copy()
+    # 워밍업 포함 전체 데이터로 지표 계산
+    df_calc = df_raw.copy()
+
+    print(f"\n데이터: {len(df_raw)} bars total, 분석: {len(df_full)} bars")
+    print(f"기간: {df_full.index[0]} ~ {df_full.index[-1]}")
+    print(f"일수: {(df_full.index[-1] - df_full.index[0]).days}일")
+
+    # ── IS/OOS 분할 ──
+    split_idx = int(len(df_full) * IS_RATIO)
+    split_ts = df_full.index[split_idx]
+    print(f"IS/OOS 분할: IS ~{split_ts.date()} | OOS {split_ts.date()}~")
+
+    # ── XRP 15m 지표 ──
+    df_calc["ema20"] = ta.ema(df_calc["close"], length=EMA_PULLBACK_LEN)
+    df_calc["vol_ma20"] = ta.sma(df_calc["volume"], length=20)
+
+    # ── XRP 1h 지표 ──
+    df_1h = build_xrp_1h(df_calc)
+    df_merged_base = merge_higher_tf(df_calc, df_1h, "1h")
+
+    # 분석 기간만 슬라이스
+    df_analysis = df_merged_base[df_merged_base.index >= df_full.index[0]].copy()
+
+    # ── 1. 베이스라인 (BTC 필터 없음) ──
+    print("\n" + "=" * 72)
+    print("  BASELINE (BTC 필터 없음)")
+    print("=" * 72)
+
+    baseline_trades = run_backtest(df_analysis, use_btc_filter=False)
+    baseline_is, baseline_oos = split_is_oos(baseline_trades, split_ts)
+
+    print_section("IS (베이스라인)", baseline_is)
+    print_section("OOS (베이스라인)", baseline_oos)
+
+    # ── 2. Sweep ──
+    print("\n" + "=" * 72)
+    print("  SWEEP (12개 조합)")
+    print("=" * 72)
+
+    combos = list(product(
+        SWEEP_GRID["btc_tf"],
+        SWEEP_GRID["btc_ema_fast"],
+        SWEEP_GRID["btc_ema_slow"],
+    ))
+
+    trade_log_path = Path(f"results/{args.symbol}/mtf_btc_filter_trades.csv")
+    trade_log_path.parent.mkdir(parents=True, exist_ok=True)
+    if trade_log_path.exists():
+        trade_log_path.unlink()
+
+    results = []
+
+    for btc_tf, ema_f, ema_s in combos:
+        if ema_f >= ema_s:
+            continue  # fast >= slow는 무의미
+
+        label = f"BTC_{btc_tf}_EMA{ema_f}/{ema_s}"
+        is_main = (btc_tf == MAIN_HYPOTHESIS["btc_tf"] and
+                   ema_f == MAIN_HYPOTHESIS["btc_ema_fast"] and
+                   ema_s == MAIN_HYPOTHESIS["btc_ema_slow"])
+
+        # BTC 지표 계산 + merge
+        df_btc = build_btc_resampled(df_calc, btc_tf, ema_f, ema_s)
+        df_with_btc = merge_higher_tf(df_analysis, df_btc, btc_tf)
+
+        # 백테스트
+        trades = run_backtest(df_with_btc, use_btc_filter=True)
+        is_trades, oos_trades = split_is_oos(trades, split_ts)
+
+        # IS 거래 수 체크
+        if len(is_trades) < MIN_IS_TRADES:
+            status = "SKIP(IS<100)"
+        else:
+            status = "MAIN" if is_main else "sweep"
+
+        # 메트릭
+        is_raw = calc_metrics([t.pnl_bps for t in is_trades])
+        is_fees = calc_metrics(apply_cost(is_trades, "fees_only"))
+        oos_raw = calc_metrics([t.pnl_bps for t in oos_trades])
+        oos_fees = calc_metrics(apply_cost(oos_trades, "fees_only"))
+        oos_real = calc_metrics(apply_cost(oos_trades, "realistic"))
+
+        # LONG/SHORT 분리 (OOS)
+        oos_long = [t for t in oos_trades if t.side == "LONG"]
+        oos_short = [t for t in oos_trades if t.side == "SHORT"]
+        oos_fees_l = calc_metrics(apply_cost(oos_long, "fees_only"))
+        oos_fees_s = calc_metrics(apply_cost(oos_short, "fees_only"))
+
+        results.append({
+            "label": label, "is_main": is_main, "status": status,
+            "is_trades": is_raw["trades"], "is_raw_pf": is_raw["pf"],
+            "is_fees_pf": is_fees["pf"],
+            "oos_trades": oos_raw["trades"], "oos_raw_pf": oos_raw["pf"],
+            "oos_fees_pf": oos_fees["pf"], "oos_real_pf": oos_real["pf"],
+            "oos_fees_pnl": oos_fees["cum_pnl"],
+            "oos_long_fees_pf": oos_fees_l["pf"], "oos_short_fees_pf": oos_fees_s["pf"],
+            "oos_long_n": oos_fees_l["trades"], "oos_short_n": oos_fees_s["trades"],
+        })
+
+        # 거래 로그 저장
+        save_trade_log(trades, trade_log_path, label)
+
+    # ── Sweep 결과 테이블 ──
+    print(f"\n  {'Label':<22} {'St':>6} {'IS_N':>5} {'IS_FPF':>6} "
+          f"{'OOS_N':>5} {'OOS_RPF':>7} {'OOS_FPF':>7} {'OOS_rPF':>7} "
+          f"{'L_FPF':>6} {'S_FPF':>6}")
+    print(f"  {'-'*92}")
+
+    for r in results:
+        marker = " ★" if r["is_main"] else ""
+        print(f"  {r['label']:<22} {r['status']:>6} {r['is_trades']:>5} {r['is_fees_pf']:>6.2f} "
+              f"{r['oos_trades']:>5} {r['oos_raw_pf']:>7.2f} {r['oos_fees_pf']:>7.2f} {r['oos_real_pf']:>7.2f} "
+              f"{r['oos_long_fees_pf']:>6.2f} {r['oos_short_fees_pf']:>6.2f}{marker}")
+
+    # ── 3. 메인 가설 상세 결과 ──
+    main_result = next((r for r in results if r["is_main"]), None)
+    if main_result is None:
+        print("\n  [ERROR] 메인 가설 결과 없음")
+        return
+
+    print("\n" + "=" * 72)
+    print(f"  메인 가설 상세: {main_result['label']}")
+    print("=" * 72)
+
+    # 메인 가설 재실행하여 상세 출력
+    df_btc_main = build_btc_resampled(
+        df_calc, MAIN_HYPOTHESIS["btc_tf"],
+        MAIN_HYPOTHESIS["btc_ema_fast"], MAIN_HYPOTHESIS["btc_ema_slow"])
+    df_main = merge_higher_tf(df_analysis, df_btc_main, MAIN_HYPOTHESIS["btc_tf"])
+    main_trades = run_backtest(df_main, use_btc_filter=True)
+    main_is, main_oos = split_is_oos(main_trades, split_ts)
+
+    print_section("IS (메인 가설)", main_is)
+    print_section("OOS (메인 가설)", main_oos)
+
+    # ── 4. 판정 ──
+    print("\n" + "=" * 72)
+    print("  판정")
+    print("=" * 72)
+
+    # 베이스라인 비교
+    bl_oos_fees = calc_metrics(apply_cost(baseline_oos, "fees_only"))
+    main_oos_fees = calc_metrics(apply_cost(main_oos, "fees_only"))
+    main_oos_real = calc_metrics(apply_cost(main_oos, "realistic"))
+
+    print(f"\n  베이스라인 OOS fees_only PF: {bl_oos_fees['pf']:.2f} ({bl_oos_fees['trades']}건)")
+    print(f"  메인 가설  OOS fees_only PF: {main_oos_fees['pf']:.2f} ({main_oos_fees['trades']}건)")
+    print(f"  메인 가설  OOS realistic PF: {main_oos_real['pf']:.2f}")
+    print(f"  개선폭: fees_only PF {main_oos_fees['pf'] - bl_oos_fees['pf']:+.2f}")
+
+    # 합격 기준 체크
+    checks = []
+    checks.append(("OOS fees_only PF >= 1.2", main_oos_fees["pf"] >= 1.2, f"{main_oos_fees['pf']:.2f}"))
+    checks.append(("OOS realistic PF >= 1.0", main_oos_real["pf"] >= 1.0, f"{main_oos_real['pf']:.2f}"))
+    checks.append(("OOS 거래수 >= 50", main_oos_fees["trades"] >= 50, f"{main_oos_fees['trades']}"))
+
+    # LONG/SHORT 대칭성
+    oos_long_t = [t for t in main_oos if t.side == "LONG"]
+    oos_short_t = [t for t in main_oos if t.side == "SHORT"]
+    l_pf = calc_metrics(apply_cost(oos_long_t, "fees_only"))["pf"]
+    s_pf = calc_metrics(apply_cost(oos_short_t, "fees_only"))["pf"]
+    checks.append(("LONG/SHORT fees PF >= 0.8", l_pf >= 0.8 and s_pf >= 0.8, f"L:{l_pf:.2f} S:{s_pf:.2f}"))
+
+    # IS/OOS 격차
+    main_is_fees = calc_metrics(apply_cost(main_is, "fees_only"))
+    if main_is_fees["pf"] > 0:
+        gap = abs(main_oos_fees["pf"] - main_is_fees["pf"]) / main_is_fees["pf"]
+    else:
+        gap = 1.0
+    checks.append(("IS/OOS PF 격차 < 30%", gap < 0.3, f"{gap*100:.1f}%"))
+
+    # 베이스라인 대비 개선
+    improvement = main_oos_fees["pf"] > bl_oos_fees["pf"]
+    checks.append(("베이스라인 대비 개선", improvement,
+                    f"{main_oos_fees['pf']:.2f} vs {bl_oos_fees['pf']:.2f}"))
+
+    print(f"\n  합격 기준 체크:")
+    all_pass = True
+    for desc, passed, val in checks:
+        icon = "PASS" if passed else "FAIL"
+        print(f"    [{icon}] {desc}: {val}")
+        if not passed:
+            all_pass = False
+
+    print()
+    if all_pass:
+        print("  ★ [최종 판정: PASS] BTC 추세 필터가 유효합니다.")
+    else:
+        print("  ✗ [최종 판정: FAIL] BTC 추세 필터로도 기준 미달. MTF 전략 폐기.")
+
+    # robustness 요약
+    passing_combos = [r for r in results if r["status"] != "SKIP(IS<100)" and r["oos_fees_pf"] >= 1.2]
+    print(f"\n  Robustness: {len(passing_combos)}/{len(results)} 조합이 OOS fees_only PF >= 1.2")
+
+    print(f"\n  거래 로그: {trade_log_path}")
+    print()
+
+
+if __name__ == "__main__":
+    main()
--- a/scripts/revalidate_apr15.py
+++ b/scripts/revalidate_apr15.py
@@ -0,0 +1,49 @@
+"""
+4월 15일 재검증 스크립트 — L/S ratio + FR×OI 동시 재실행
+
+crontab: 0 10 15 4 * cd /root/cointrader && /root/cointrader/.venv/bin/python scripts/revalidate_apr15.py
+
+재검증 대상:
+1. L/S ratio (top_acct_ls_ratio) — 24일 데이터로 6개 조합
+2. FR × OI변화율(1h) — 29일 데이터로 12개 조합
+3. 대칭성 재판정
+
+Usage: python scripts/revalidate_apr15.py
+"""
+
+import subprocess
+import sys
+from datetime import datetime, timezone
+
+def main():
+    now = datetime.now(timezone.utc)
+    print("=" * 80)
+    print(f"  4월 재검증 실행 — {now.strftime('%Y-%m-%d %H:%M UTC')}")
+    print("=" * 80)
+
+    print("\n[1/2] L/S ratio 백테스트 재실행")
+    print("-" * 40)
+    r1 = subprocess.run(
+        [sys.executable, "scripts/ls_ratio_backtest.py"],
+        capture_output=False,
+    )
+
+    print("\n\n[2/2] FR × OI 백테스트 재실행")
+    print("-" * 40)
+    r2 = subprocess.run(
+        [sys.executable, "scripts/fr_oi_backtest.py"],
+        capture_output=False,
+    )
+
+    print("\n" + "=" * 80)
+    print("  재검증 완료")
+    print("=" * 80)
+    print(f"\n  L/S ratio: {'성공' if r1.returncode == 0 else '실패'}")
+    print(f"  FR × OI:   {'성공' if r2.returncode == 0 else '실패'}")
+    print(f"\n  판정 기준:")
+    print(f"    - L/S ratio: PF > 1.0인 조합 있으면 재검토")
+    print(f"    - FR × OI: SHORT+LONG 모두 PF > 1.0이면 대칭성 통과")
+    print(f"    - 둘 다 실패 시 확정 폐기")
+
+if __name__ == "__main__":
+    main()
--- a/scripts/trade_ls_analysis.py
+++ b/scripts/trade_ls_analysis.py
@@ -0,0 +1,459 @@
+"""
+Trade History + L/S Ratio 종합 분석
+- 봇 대시보드 API에서 거래 기록 로드
+- Binance API에서 L/S ratio (30일) 로드 + 로컬 parquet 병합
+- 진입/청산 시점 L/S ratio 매칭
+- 수익/손실 거래별 L/S 분포 분석
+- L/S 임계값 필터링 시뮬레이션
+
+Usage: python scripts/trade_ls_analysis.py [--api URL]
+"""
+
+import asyncio
+import aiohttp
+import pandas as pd
+import numpy as np
+from datetime import datetime, timedelta, timezone
+from pathlib import Path
+import argparse
+import json
+
+BASE = "https://fapi.binance.com"
+DASHBOARD_API = "http://10.1.10.24:8080/api/trades"
+DATA_DIR = Path("data")
+SYMBOLS_FOR_LS = ["XRPUSDT", "BTCUSDT", "ETHUSDT"]
+
+
+async def fetch_json(session, url, params=None):
+    async with session.get(url, params=params) as resp:
+        return await resp.json()
+
+
+async def fetch_ls_ratios_from_api(session, symbol, start_ms, end_ms):
+    """Binance API에서 L/S ratio 전체 기간 가져오기 (페이징)"""
+    all_top_acct = []
+    all_global = []
+
+    for endpoint, target in [
+        (f"{BASE}/futures/data/topLongShortAccountRatio", all_top_acct),
+        (f"{BASE}/futures/data/globalLongShortAccountRatio", all_global),
+    ]:
+        current = start_ms
+        while current < end_ms:
+            params = {
+                "symbol": symbol,
+                "period": "15m",
+                "startTime": current,
+                "endTime": end_ms,
+                "limit": 500,
+            }
+            data = await fetch_json(session, endpoint, params)
+            if not data or not isinstance(data, list):
+                break
+            target.extend(data)
+            last_ts = int(data[-1]["timestamp"])
+            if last_ts <= current:
+                break
+            current = last_ts + 1
+
+    def to_df(data, col_name):
+        if not data:
+            return pd.DataFrame()
+        df = pd.DataFrame(data)
+        df["timestamp"] = pd.to_datetime(df["timestamp"].astype(int), unit="ms", utc=True)
+        df[col_name] = df["longShortRatio"].astype(float)
+        return df[["timestamp", col_name]].drop_duplicates("timestamp")
+
+    df_top = to_df(all_top_acct, "top_acct_ls_ratio")
+    df_global = to_df(all_global, "global_ls_ratio")
+
+    if df_top.empty and df_global.empty:
+        return pd.DataFrame()
+
+    if df_top.empty:
+        return df_global
+    if df_global.empty:
+        return df_top
+
+    return df_top.merge(df_global, on="timestamp", how="outer").sort_values("timestamp")
+
+
+def load_local_ls_ratio(symbol):
+    """로컬 parquet에서 L/S ratio 로드"""
+    path = DATA_DIR / symbol.lower() / "ls_ratio_15m.parquet"
+    if not path.exists():
+        return pd.DataFrame()
+    df = pd.read_parquet(path)
+    if "timestamp" in df.columns:
+        df["timestamp"] = pd.to_datetime(df["timestamp"], utc=True)
+    return df
+
+
+def find_nearest_ls(ls_df, target_time, max_gap_minutes=30):
+    """타겟 시간에 가장 가까운 L/S ratio 찾기"""
+    if ls_df.empty:
+        return None, None, None
+
+    target = pd.Timestamp(target_time, tz="UTC")
+    diffs = (ls_df["timestamp"] - target).abs()
+    idx = diffs.idxmin()
+    gap = diffs[idx]
+
+    if gap > pd.Timedelta(minutes=max_gap_minutes):
+        return None, None, gap
+
+    row = ls_df.loc[idx]
+    return row.get("top_acct_ls_ratio"), row.get("global_ls_ratio"), gap
+
+
+def classify_signal(trade):
+    """진입 신호 분류"""
+    rsi = trade.get("rsi", 0)
+    macd = trade.get("macd_hist", 0)
+    direction = trade["direction"]
+
+    signals = []
+    if direction == "LONG":
+        if rsi and rsi > 65:
+            signals.append("RSI과매수진입")
+        elif rsi and rsi < 35:
+            signals.append("RSI역방향")
+        if macd and macd > 0:
+            signals.append("MACD+")
+        elif macd and macd < 0:
+            signals.append("MACD역방향")
+    else:  # SHORT
+        if rsi and rsi < 35:
+            signals.append("RSI과매도진입")
+        elif rsi and rsi > 65:
+            signals.append("RSI역방향")
+        if macd and macd < 0:
+            signals.append("MACD-")
+        elif macd and macd > 0:
+            signals.append("MACD역방향")
+
+    return ", ".join(signals) if signals else "복합신호"
+
+
+def classify_close_reason(trade):
+    """청산 이유 분류"""
+    reason = trade["close_reason"]
+    if reason == "TP":
+        return "TP(익절)"
+    elif reason == "SYNC":
+        return "SL(손절)"
+    elif reason == "MANUAL":
+        # MANUAL인데 SL가격과 exit가격이 같으면 SL
+        sl = trade.get("sl")
+        exit_p = trade.get("exit_price")
+        if sl and exit_p and abs(float(sl) - float(exit_p)) < 0.0001:
+            return "SL(손절)"
+        # 역방향 시그널로 청산
+        extra = trade.get("extra", "{}")
+        if isinstance(extra, str):
+            try:
+                extra = json.loads(extra)
+            except json.JSONDecodeError:
+                extra = {}
+        if extra.get("recovery"):
+            return "신호반전"
+        return "SL(손절)"  # 대부분 MANUAL은 SL 히트
+    return reason
+
+
+async def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--api", default=DASHBOARD_API)
+    args = parser.parse_args()
+
+    print("=" * 80)
+    print("  Trade History + L/S Ratio 종합 분석")
+    print("=" * 80)
+
+    # 1. 거래 데이터 로드
+    async with aiohttp.ClientSession() as session:
+        trade_data = await fetch_json(session, args.api)
+        trades = trade_data["trades"]
+        print(f"\n📊 거래 데이터: {len(trades)}건 로드")
+
+        # 2. L/S ratio 데이터 로드 (API + local)
+        # 가장 오래된 거래 기준으로 시작 시간 설정
+        earliest = min(t["entry_time"] for t in trades)
+        start_dt = pd.Timestamp(earliest, tz="UTC") - timedelta(hours=1)
+        end_dt = datetime.now(timezone.utc)
+        start_ms = int(start_dt.timestamp() * 1000)
+        end_ms = int(end_dt.timestamp() * 1000)
+
+        print(f"📡 Binance API에서 L/S ratio 로딩 ({start_dt.date()} ~ {end_dt.date()})...")
+
+        ls_data = {}
+        for sym in SYMBOLS_FOR_LS:
+            api_df = await fetch_ls_ratios_from_api(session, sym, start_ms, end_ms)
+            local_df = load_local_ls_ratio(sym)
+
+            if not api_df.empty and not local_df.empty:
+                combined = pd.concat([api_df, local_df]).drop_duplicates("timestamp").sort_values("timestamp")
+            elif not api_df.empty:
+                combined = api_df
+            elif not local_df.empty:
+                combined = local_df
+            else:
+                combined = pd.DataFrame()
+
+            ls_data[sym] = combined.reset_index(drop=True)
+            print(f"  {sym}: {len(ls_data[sym])} rows ({ls_data[sym]['timestamp'].min()} ~ {ls_data[sym]['timestamp'].max()})" if not combined.empty else f"  {sym}: no data")
+
+    # 3. 거래별 L/S ratio 매칭
+    print("\n" + "=" * 80)
+    print("  1. 거래 기록 + L/S Ratio 매칭")
+    print("=" * 80)
+
+    enriched = []
+    for t in trades:
+        sym = t["symbol"]
+        # XRP 거래에는 XRP L/S, 다른 심볼도 XRP L/S 참조 (크로스 분석)
+        ls_sym = ls_data.get(sym, pd.DataFrame())
+        ls_xrp = ls_data.get("XRPUSDT", pd.DataFrame())
+        ls_btc = ls_data.get("BTCUSDT", pd.DataFrame())
+
+        entry_top, entry_global, _ = find_nearest_ls(ls_sym if not ls_sym.empty else ls_xrp, t["entry_time"])
+        exit_top, exit_global, _ = find_nearest_ls(ls_sym if not ls_sym.empty else ls_xrp, t["exit_time"])
+
+        # BTC L/S for cross-reference
+        btc_entry_top, btc_entry_global, _ = find_nearest_ls(ls_btc, t["entry_time"])
+
+        enriched.append({
+            "id": t["id"],
+            "symbol": sym,
+            "direction": t["direction"],
+            "entry_time": t["entry_time"],
+            "exit_time": t["exit_time"],
+            "signal": classify_signal(t),
+            "close_reason": classify_close_reason(t),
+            "rsi": t.get("rsi"),
+            "macd_hist": t.get("macd_hist"),
+            "entry_top_acct_ls": entry_top,
+            "entry_global_ls": entry_global,
+            "exit_top_acct_ls": exit_top,
+            "exit_global_ls": exit_global,
+            "ls_change_top": (exit_top - entry_top) if entry_top and exit_top else None,
+            "ls_change_global": (exit_global - entry_global) if entry_global and exit_global else None,
+            "btc_entry_top_ls": btc_entry_top,
+            "btc_entry_global_ls": btc_entry_global,
+            "net_pnl": t["net_pnl"],
+            "is_win": t["net_pnl"] > 0,
+            "entry_price": t["entry_price"],
+            "exit_price": t["exit_price"],
+        })
+
+    df = pd.DataFrame(enriched)
+
+    # 거래 기록 테이블 출력
+    print(f"\n{'ID':>3} {'심볼':<10} {'방향':<5} {'진입시간':<20} {'진입신호':<16} "
+          f"{'진입L/S':>7} {'청산L/S':>7} {'ΔL/S':>7} {'청산이유':<10} {'PnL':>8}")
+    print("-" * 120)
+    for _, r in df.iterrows():
+        entry_ls = f"{r['entry_top_acct_ls']:.3f}" if pd.notna(r['entry_top_acct_ls']) else "N/A"
+        exit_ls = f"{r['exit_top_acct_ls']:.3f}" if pd.notna(r['exit_top_acct_ls']) else "N/A"
+        delta_ls = f"{r['ls_change_top']:+.3f}" if pd.notna(r['ls_change_top']) else "N/A"
+        pnl_str = f"{r['net_pnl']:+.4f}"
+        print(f"{r['id']:>3} {r['symbol']:<10} {r['direction']:<5} {r['entry_time']:<20} {r['signal']:<16} "
+              f"{entry_ls:>7} {exit_ls:>7} {delta_ls:>7} {r['close_reason']:<10} {pnl_str:>8}")
+
+    # 4. 수익 거래 vs 손실 거래 L/S 비교
+    print("\n" + "=" * 80)
+    print("  2. 수익 거래 vs 손실 거래: L/S Ratio 비교")
+    print("=" * 80)
+
+    has_ls = df.dropna(subset=["entry_top_acct_ls"])
+    if len(has_ls) > 0:
+        wins = has_ls[has_ls["is_win"]]
+        losses = has_ls[~has_ls["is_win"]]
+
+        print(f"\n  L/S ratio 매칭된 거래: {len(has_ls)}건 (수익: {len(wins)}, 손실: {len(losses)})")
+        print(f"\n  {'지표':<30} {'수익 거래':>12} {'손실 거래':>12} {'차이':>10}")
+        print("  " + "-" * 70)
+
+        for col, label in [
+            ("entry_top_acct_ls", "진입 시 top_acct L/S"),
+            ("entry_global_ls", "진입 시 global L/S"),
+            ("exit_top_acct_ls", "청산 시 top_acct L/S"),
+            ("exit_global_ls", "청산 시 global L/S"),
+            ("ls_change_top", "진입→청산 ΔL/S (top)"),
+            ("ls_change_global", "진입→청산 ΔL/S (global)"),
+            ("btc_entry_top_ls", "BTC 진입 시 top_acct L/S"),
+        ]:
+            w_vals = wins[col].dropna()
+            l_vals = losses[col].dropna()
+            if len(w_vals) > 0 and len(l_vals) > 0:
+                w_mean = w_vals.mean()
+                l_mean = l_vals.mean()
+                diff = w_mean - l_mean
+                print(f"  {label:<30} {w_mean:>12.4f} {l_mean:>12.4f} {diff:>+10.4f}")
+            else:
+                w_str = f"{w_vals.mean():.4f}" if len(w_vals) > 0 else "N/A"
+                l_str = f"{l_vals.mean():.4f}" if len(l_vals) > 0 else "N/A"
+                print(f"  {label:<30} {w_str:>12} {l_str:>12} {'N/A':>10}")
+    else:
+        print("\n  ⚠️ L/S ratio 매칭 가능한 거래가 없습니다")
+
+    # 5. 진입 시점 L/S와 거래 결과의 상관계수
+    print("\n" + "=" * 80)
+    print("  3. L/S Ratio ↔ PnL 상관계수")
+    print("=" * 80)
+
+    for col, label in [
+        ("entry_top_acct_ls", "진입 top_acct L/S"),
+        ("entry_global_ls", "진입 global L/S"),
+        ("btc_entry_top_ls", "BTC 진입 top_acct L/S"),
+        ("ls_change_top", "ΔL/S (top)"),
+    ]:
+        valid = df.dropna(subset=[col, "net_pnl"])
+        if len(valid) >= 3:
+            corr = valid[col].corr(valid["net_pnl"])
+            print(f"  {label:<30} r = {corr:>+.4f}  (n={len(valid)})")
+        else:
+            print(f"  {label:<30} 데이터 부족 (n={len(valid)})")
+
+    # 6. 방향별 분석 (LONG 진입 시 L/S 높으면? SHORT 진입 시 낮으면?)
+    print("\n" + "=" * 80)
+    print("  4. 방향별 L/S Ratio 분석")
+    print("=" * 80)
+
+    for direction in ["LONG", "SHORT"]:
+        subset = has_ls[has_ls["direction"] == direction]
+        if len(subset) == 0:
+            continue
+        print(f"\n  [{direction}] ({len(subset)}건)")
+        wins_d = subset[subset["is_win"]]
+        losses_d = subset[~subset["is_win"]]
+        print(f"    수익: {len(wins_d)}건, 손실: {len(losses_d)}건")
+        if len(subset) > 0:
+            for col in ["entry_top_acct_ls", "entry_global_ls"]:
+                vals = subset[col].dropna()
+                if len(vals) > 0:
+                    w = wins_d[col].dropna()
+                    l = losses_d[col].dropna()
+                    w_str = f"{w.mean():.4f}" if len(w) > 0 else "N/A"
+                    l_str = f"{l.mean():.4f}" if len(l) > 0 else "N/A"
+                    print(f"    {col}: 수익평균={w_str}, 손실평균={l_str}")
+
+    # 7. 청산 이유별 L/S ratio 분포
+    print("\n" + "=" * 80)
+    print("  5. 청산 이유별 L/S Ratio 분포")
+    print("=" * 80)
+
+    for reason in df["close_reason"].unique():
+        subset = has_ls[has_ls["close_reason"] == reason]
+        if len(subset) == 0:
+            continue
+        print(f"\n  [{reason}] ({len(subset)}건)")
+        for col, label in [("entry_top_acct_ls", "진입 L/S"), ("exit_top_acct_ls", "청산 L/S"), ("ls_change_top", "ΔL/S")]:
+            vals = subset[col].dropna()
+            if len(vals) > 0:
+                print(f"    {label}: mean={vals.mean():.4f}, std={vals.std():.4f}, min={vals.min():.4f}, max={vals.max():.4f}")
+
+    # 8. L/S 임계값 필터링 시뮬레이션
+    print("\n" + "=" * 80)
+    print("  6. L/S 임계값 필터링 시뮬레이션")
+    print("  '만약 L/S 조건으로 진입을 필터링했다면?'")
+    print("=" * 80)
+
+    if len(has_ls) > 0:
+        # 시뮬레이션 1: top_acct L/S ratio 기준 필터
+        print("\n  [A] top_acct_ls_ratio 임계값별 (LONG 진입 시 ratio > threshold)")
+        print(f"  {'Threshold':>10} {'통과':>5} {'차단':>5} {'통과 PnL':>10} {'차단 PnL':>10} {'통과 승률':>10} {'원본 승률':>10}")
+        print("  " + "-" * 70)
+
+        longs = has_ls[has_ls["direction"] == "LONG"]
+        shorts = has_ls[has_ls["direction"] == "SHORT"]
+        all_wr = has_ls["is_win"].mean() * 100 if len(has_ls) > 0 else 0
+
+        if len(longs) > 0:
+            ls_vals = longs["entry_top_acct_ls"].dropna()
+            if len(ls_vals) > 0:
+                for pct in [0.25, 0.50, 0.75]:
+                    threshold = ls_vals.quantile(pct)
+                    passed = longs[longs["entry_top_acct_ls"] >= threshold]
+                    blocked = longs[longs["entry_top_acct_ls"] < threshold]
+                    p_pnl = passed["net_pnl"].sum()
+                    b_pnl = blocked["net_pnl"].sum()
+                    p_wr = passed["is_win"].mean() * 100 if len(passed) > 0 else 0
+                    print(f"  {threshold:>10.4f} {len(passed):>5} {len(blocked):>5} "
+                          f"{p_pnl:>+10.4f} {b_pnl:>+10.4f} {p_wr:>9.1f}% {all_wr:>9.1f}%")
+
+        # 시뮬레이션 2: SHORT 진입 시 ratio < threshold
+        print(f"\n  [B] top_acct_ls_ratio 임계값별 (SHORT 진입 시 ratio < threshold)")
+        print(f"  {'Threshold':>10} {'통과':>5} {'차단':>5} {'통과 PnL':>10} {'차단 PnL':>10} {'통과 승률':>10}")
+        print("  " + "-" * 70)
+
+        if len(shorts) > 0:
+            ls_vals = shorts["entry_top_acct_ls"].dropna()
+            if len(ls_vals) > 0:
+                for pct in [0.75, 0.50, 0.25]:
+                    threshold = ls_vals.quantile(pct)
+                    passed = shorts[shorts["entry_top_acct_ls"] <= threshold]
+                    blocked = shorts[shorts["entry_top_acct_ls"] > threshold]
+                    p_pnl = passed["net_pnl"].sum()
+                    b_pnl = blocked["net_pnl"].sum()
+                    p_wr = passed["is_win"].mean() * 100 if len(passed) > 0 else 0
+                    print(f"  {threshold:>10.4f} {len(passed):>5} {len(blocked):>5} "
+                          f"{p_pnl:>+10.4f} {b_pnl:>+10.4f} {p_wr:>9.1f}%")
+
+        # 시뮬레이션 3: Momentum 전략 - L/S 방향과 같은 방향만 진입
+        print(f"\n  [C] Momentum 필터: L/S ratio > 중앙값이면 LONG만, < 중앙값이면 SHORT만")
+        if len(has_ls) > 0:
+            median_ls = has_ls["entry_top_acct_ls"].median()
+            momentum_filter = has_ls.apply(
+                lambda r: (r["direction"] == "LONG" and r["entry_top_acct_ls"] >= median_ls) or
+                          (r["direction"] == "SHORT" and r["entry_top_acct_ls"] < median_ls),
+                axis=1
+            )
+            passed = has_ls[momentum_filter]
+            blocked = has_ls[~momentum_filter]
+            print(f"    중앙값: {median_ls:.4f}")
+            print(f"    통과: {len(passed)}건, PnL합계: {passed['net_pnl'].sum():+.4f}, "
+                  f"승률: {passed['is_win'].mean()*100:.1f}%")
+            print(f"    차단: {len(blocked)}건, PnL합계: {blocked['net_pnl'].sum():+.4f}, "
+                  f"승률: {blocked['is_win'].mean()*100:.1f}%")
+
+        # 시뮬레이션 4: Contrarian 전략 - L/S 반대 방향만 진입
+        print(f"\n  [D] Contrarian 필터: L/S ratio > 중앙값이면 SHORT만, < 중앙값이면 LONG만")
+        if len(has_ls) > 0:
+            contrarian_filter = has_ls.apply(
+                lambda r: (r["direction"] == "SHORT" and r["entry_top_acct_ls"] >= median_ls) or
+                          (r["direction"] == "LONG" and r["entry_top_acct_ls"] < median_ls),
+                axis=1
+            )
+            passed = has_ls[contrarian_filter]
+            blocked = has_ls[~contrarian_filter]
+            print(f"    통과: {len(passed)}건, PnL합계: {passed['net_pnl'].sum():+.4f}, "
+                  f"승률: {passed['is_win'].mean()*100:.1f}%")
+            print(f"    차단: {len(blocked)}건, PnL합계: {blocked['net_pnl'].sum():+.4f}, "
+                  f"승률: {blocked['is_win'].mean()*100:.1f}%")
+
+    # 9. 전체 L/S ratio 시계열 + 거래 오버레이 요약
+    print("\n" + "=" * 80)
+    print("  7. 전체 요약")
+    print("=" * 80)
+
+    total_trades = len(df)
+    ls_matched = len(has_ls)
+    total_pnl = df["net_pnl"].sum()
+    win_rate = df["is_win"].mean() * 100
+    print(f"\n  전체 거래: {total_trades}건 (L/S 매칭: {ls_matched}건)")
+    print(f"  총 PnL: {total_pnl:+.4f} USDT")
+    print(f"  승률: {win_rate:.1f}% ({df['is_win'].sum()}/{total_trades})")
+
+    if len(has_ls) > 0:
+        print(f"\n  L/S 매칭 거래 통계:")
+        print(f"    진입 top_acct L/S 범위: {has_ls['entry_top_acct_ls'].min():.4f} ~ {has_ls['entry_top_acct_ls'].max():.4f}")
+        print(f"    진입 global L/S 범위: {has_ls['entry_global_ls'].min():.4f} ~ {has_ls['entry_global_ls'].max():.4f}")
+
+    print(f"\n  ⚠️  주의: 거래 {total_trades}건은 통계적 유의성이 부족합니다.")
+    print(f"  현재 결과는 탐색적 분석이며, 최소 50건 이상의 거래가 필요합니다.")
+    print(f"  L/S ratio 데이터는 계속 축적 중이므로 4월 말 재분석을 권장합니다.")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
--- a/src/config.py
+++ b/src/config.py
@@ -106,3 +106,21 @@ class Config:
            volume_multiplier=self.volume_multiplier,
        ))

+
+# ── OOS 사후보정용 비용 모델 ──────────────────────────────────────
+COST_MODEL = {
+    "taker_fee_bps": 4.0,       # Binance USDⓈ-M Futures VIP 0
+    "maker_fee_bps": 2.0,       # 향후 limit TP 도입 대비
+    # MTF bot 주문 타입 (현재 전부 MARKET = taker)
+    "entry_order_type": "taker",
+    "sl_order_type": "taker",
+    "tp_order_type": "taker",
+}
+
+# 3개 프리셋 시나리오 (확장 금지, 이 셋으로 고정)
+COST_SCENARIOS = {
+    "fees_only":   {"slippage_bps_per_side": 0.0, "funding_bps_per_8h": 0.0},
+    "realistic":   {"slippage_bps_per_side": 1.0, "funding_bps_per_8h": 1.0},
+    "pessimistic": {"slippage_bps_per_side": 3.0, "funding_bps_per_8h": 2.0},
+}
+
--- a/src/mtf_bot.py
+++ b/src/mtf_bot.py
@@ -390,6 +390,21 @@ class TriggerStrategy:

 _MTF_TRADE_DIR = Path("data/trade_history")

+# ── 킬스위치 상수 (bot.py와 동일 기준) ──
+_FAST_KILL_STREAK = 8           # 연속 손실 N회 → 즉시 중단
+_SLOW_KILL_WINDOW = 15          # 최근 N거래 PF 산출
+_SLOW_KILL_PF_THRESHOLD = 0.75  # PF < 이 값이면 중단
+
+
+def _tail_lines(path: Path, n: int) -> list[str]:
+    """파일의 마지막 n줄을 읽는다."""
+    try:
+        with open(path) as f:
+            lines = f.readlines()
+        return lines[-n:]
+    except Exception:
+        return []
+

 class ExecutionManager:
    """
@@ -408,6 +423,11 @@ class ExecutionManager:
        self._sl_price: Optional[float] = None
        self._tp_price: Optional[float] = None
        self._atr_at_entry: Optional[float] = None
+        # ── 킬스위치 ──
+        self._killed: bool = False
+        self._trade_history: list[dict] = []
+        self._restore_trade_history()
+        self._restore_kill_switch()

    def execute(self, signal: str, current_price: float, atr_value: Optional[float]) -> Optional[Dict]:
        """
@@ -424,6 +444,10 @@ class ExecutionManager:
        if signal == "HOLD":
            return None

+        if self._killed:
+            logger.warning(f"[ExecutionManager] 킬스위치 발동 상태 — 신규 진입 차단 (신호={signal})")
+            return None
+
        if self.current_position is not None:
            logger.debug(
                f"[ExecutionManager] 포지션 중복 차단: "
@@ -503,6 +527,10 @@ class ExecutionManager:
        # JSONL에 기록
        self._save_trade(reason, exit_price, pnl_bps)

+        # ── 킬스위치: 거래 이력 추가 + 판정 ──
+        self._append_trade_history(pnl_bps)
+        self._check_kill_switch()
+
        # ── 실주문 (프로덕션 전환 시 주석 해제) ──
        # if self.current_position == "LONG":
        #     await self.exchange.create_market_sell_order(symbol, amount)
@@ -540,6 +568,91 @@ class ExecutionManager:
        except Exception as e:
            logger.warning(f"[ExecutionManager] 거래 기록 저장 실패: {e}")

+    # ── 킬스위치 ──────────────────────────────────────────────────────
+
+    def _trade_history_path(self) -> Path:
+        _MTF_TRADE_DIR.mkdir(parents=True, exist_ok=True)
+        return _MTF_TRADE_DIR / f"mtf_{self.symbol.replace('/', '').replace(':', '').lower()}.jsonl"
+
+    def _restore_trade_history(self) -> None:
+        """부팅 시 JSONL에서 최근 N건의 pnl_bps를 복원한다."""
+        path = self._trade_history_path()
+        if not path.exists():
+            return
+        try:
+            tail_n = max(_FAST_KILL_STREAK, _SLOW_KILL_WINDOW)
+            lines = _tail_lines(path, tail_n)
+            for line in lines:
+                line = line.strip()
+                if line:
+                    record = json.loads(line)
+                    self._trade_history.append({"pnl_bps": record.get("pnl_bps", 0.0)})
+            logger.info(
+                f"[ExecutionManager] 거래 이력 복원: {len(self._trade_history)}건"
+            )
+        except Exception as e:
+            logger.warning(f"[ExecutionManager] 거래 이력 복원 실패: {e}")
+
+    def _restore_kill_switch(self) -> None:
+        """부팅 시 리셋 플래그 확인 후, 이력 기반으로 킬스위치 소급 검증."""
+        reset_key = f"RESET_KILL_SWITCH_MTF_{self.symbol.replace('/', '').replace(':', '').upper()}"
+        if os.environ.get(reset_key, "").lower() == "true":
+            logger.info(f"[ExecutionManager] 킬스위치 수동 해제 감지 ({reset_key}=True)")
+            self._killed = False
+            return
+        if self._check_kill_switch(silent=True):
+            logger.warning("[ExecutionManager] 부팅 시 킬스위치 조건 충족 — 신규 진입 차단")
+
+    def _append_trade_history(self, pnl_bps: float) -> None:
+        """킬스위치 판단용 거래 이력에 추가한다."""
+        self._trade_history.append({"pnl_bps": round(pnl_bps, 1)})
+        max_window = max(_FAST_KILL_STREAK, _SLOW_KILL_WINDOW)
+        if len(self._trade_history) > max_window * 2:
+            self._trade_history = self._trade_history[-max_window:]
+
+    def _check_kill_switch(self, silent: bool = False) -> bool:
+        """킬스위치 조건을 검사하고, 발동 시 True를 반환한다.
+
+        Fast Kill: 최근 8연속 손실 (pnl_bps < 0)
+        Slow Kill: 최근 15거래 PF < 0.75
+        """
+        trades = self._trade_history
+        if not trades:
+            return False
+
+        # Fast Kill
+        if len(trades) >= _FAST_KILL_STREAK:
+            recent = trades[-_FAST_KILL_STREAK:]
+            if all(t["pnl_bps"] < 0 for t in recent):
+                reason = f"Fast Kill ({_FAST_KILL_STREAK}연속 손실)"
+                self._trigger_kill_switch(reason, silent)
+                return True
+
+        # Slow Kill
+        if len(trades) >= _SLOW_KILL_WINDOW:
+            recent = trades[-_SLOW_KILL_WINDOW:]
+            gross_profit = sum(t["pnl_bps"] for t in recent if t["pnl_bps"] > 0)
+            gross_loss = abs(sum(t["pnl_bps"] for t in recent if t["pnl_bps"] < 0))
+            if gross_loss > 0:
+                pf = gross_profit / gross_loss
+                if pf < _SLOW_KILL_PF_THRESHOLD:
+                    reason = f"Slow Kill (최근 {_SLOW_KILL_WINDOW}거래 PF={pf:.2f})"
+                    self._trigger_kill_switch(reason, silent)
+                    return True
+
+        return False
+
+    def _trigger_kill_switch(self, reason: str, silent: bool = False) -> None:
+        """킬스위치 발동: 상태 변경 + 로그."""
+        self._killed = True
+        msg = (
+            f"[MTF KILL SWITCH] {self.symbol} 신규 진입 중단\n"
+            f"사유: {reason}\n"
+            f"기존 포지션 SL/TP는 정상 작동합니다.\n"
+            f"해제: RESET_KILL_SWITCH_MTF_{self.symbol.replace('/', '').replace(':', '').upper()}=True 후 재시작"
+        )
+        logger.error(msg)
+
    def get_position_info(self) -> Dict:
        """현재 포지션 정보 반환."""
        return {
--- a/tests/test_evaluate_oos.py
+++ b/tests/test_evaluate_oos.py
@@ -0,0 +1,181 @@
+"""
+evaluate_oos.py 비용 모델 단위 테스트
+"""
+
+import sys
+from pathlib import Path
+
+import pandas as pd
+import pytest
+
+# 프로젝트 루트를 path에 추가
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+from scripts.evaluate_oos import (
+    apply_cost_model,
+    calc_metrics,
+    calc_trade_cost,
+    count_funding_events,
+)
+from src.config import COST_MODEL, COST_SCENARIOS
+
+
+# ── count_funding_events 테스트 ──────────────────────────────────
+
+
+def test_count_funding_events_no_crossing():
+    """진입 01:00 UTC -> 청산 05:00 UTC, 펀딩 경계(00/08/16) 미포함 -> count == 0."""
+    entry = pd.Timestamp("2026-04-10 01:00:00+00:00")
+    exit_ = pd.Timestamp("2026-04-10 05:00:00+00:00")
+    assert count_funding_events(entry, exit_) == 0
+
+
+def test_count_funding_events_single_crossing():
+    """진입 06:00 UTC -> 청산 10:00 UTC, 08:00 포함 -> count == 1."""
+    entry = pd.Timestamp("2026-04-10 06:00:00+00:00")
+    exit_ = pd.Timestamp("2026-04-10 10:00:00+00:00")
+    assert count_funding_events(entry, exit_) == 1
+
+
+def test_count_funding_events_multiple_crossings():
+    """12시간 보유: 02:00 -> 14:00, 08:00 포함 -> count == 1."""
+    entry = pd.Timestamp("2026-04-10 02:00:00+00:00")
+    exit_ = pd.Timestamp("2026-04-10 14:00:00+00:00")
+    assert count_funding_events(entry, exit_) == 1
+
+    # 22:00 -> 10:00 (다음날), 00:00 + 08:00 포함 -> count == 2
+    entry2 = pd.Timestamp("2026-04-10 22:00:00+00:00")
+    exit2 = pd.Timestamp("2026-04-11 10:00:00+00:00")
+    assert count_funding_events(entry2, exit2) == 2
+
+
+def test_count_funding_events_short_trade_no_overcounting():
+    """75분 거래, 경계 미포함 -> count == 0."""
+    # 18:15 -> 19:30, 펀딩 경계 없음
+    entry = pd.Timestamp("2026-04-10 18:15:00+00:00")
+    exit_ = pd.Timestamp("2026-04-10 19:30:00+00:00")
+    assert count_funding_events(entry, exit_) == 0
+
+
+def test_count_funding_events_exact_boundary():
+    """정확히 경계에서 진입/청산하는 경우."""
+    # entry=08:00, exit=16:00 -> ceil(08:00)=08:00, floor(16:00)=16:00
+    # hours: 08, 09, ..., 16 -> 08:00(yes), 16:00(yes) -> count == 2
+    entry = pd.Timestamp("2026-04-10 08:00:00+00:00")
+    exit_ = pd.Timestamp("2026-04-10 16:00:00+00:00")
+    assert count_funding_events(entry, exit_) == 2
+
+
+# ── 비용 계산 테스트 ─────────────────────────────────────────────
+
+
+def test_cost_calculation_taker_roundtrip():
+    """진입 taker + SL taker, slippage 0, funding 0 -> 8 bps."""
+    row = pd.Series({
+        "entry_ts": pd.Timestamp("2026-04-10 01:00:00+00:00"),
+        "exit_ts": pd.Timestamp("2026-04-10 02:00:00+00:00"),
+        "pnl_bps": -50.0,
+        "reason": "SL 히트 (1.3012)",
+        "side": "SHORT",
+    })
+    scenario = COST_SCENARIOS["fees_only"]
+    cost = calc_trade_cost(row, scenario)
+    assert cost == 8.0  # taker(4) + taker(4) + 0 + 0
+
+
+def test_cost_calculation_tp_exit():
+    """TP 히트 시에도 현재 설정에서는 taker -> 8 bps."""
+    row = pd.Series({
+        "entry_ts": pd.Timestamp("2026-04-10 01:00:00+00:00"),
+        "exit_ts": pd.Timestamp("2026-04-10 02:00:00+00:00"),
+        "pnl_bps": 80.0,
+        "reason": "TP 히트 (1.3826)",
+        "side": "LONG",
+    })
+    scenario = COST_SCENARIOS["fees_only"]
+    cost = calc_trade_cost(row, scenario)
+    assert cost == 8.0
+
+
+def test_cost_with_slippage_and_funding():
+    """realistic 시나리오: fee 8 + slippage 2 + funding 1 = 11 bps."""
+    # 진입 15:45, 청산 17:00 -> funding event at 16:00 -> count=1
+    row = pd.Series({
+        "entry_ts": pd.Timestamp("2026-04-02 15:45:00+00:00"),
+        "exit_ts": pd.Timestamp("2026-04-02 17:00:00+00:00"),
+        "pnl_bps": -68.0,
+        "reason": "SL 히트 (1.3012)",
+        "side": "SHORT",
+    })
+    scenario = COST_SCENARIOS["realistic"]
+    cost = calc_trade_cost(row, scenario)
+    # fee=8, slippage=1*2=2, funding=1*1=1 -> total=11
+    assert cost == 11.0
+
+
+def test_adjusted_pnl_matches_manual():
+    """첫 번째 거래(Trade #0)에 대해 수작업 계산값과 일치 확인."""
+    # Trade #0: SHORT, entry 15:45 UTC, exit 17:00 UTC, pnl_bps=-68.0, SL 히트
+    # fees_only: cost=8 (fee only, funding event at 16:00 but funding_bps=0) -> adjusted=-76.0
+    # realistic: cost=8+2+1=11 -> adjusted=-79.0
+    # pessimistic: cost=8+6+2=16 -> adjusted=-84.0
+    row = pd.Series({
+        "entry_ts": pd.Timestamp("2026-04-02 15:45:02.285284+00:00"),
+        "exit_ts": pd.Timestamp("2026-04-02 17:00:00.791551+00:00"),
+        "pnl_bps": -68.0,
+        "reason": "SL 히트 (1.3012)",
+        "side": "SHORT",
+    })
+
+    for scenario_name, expected_adj in [
+        ("fees_only", -76.0),
+        ("realistic", -79.0),
+        ("pessimistic", -84.0),
+    ]:
+        scenario = COST_SCENARIOS[scenario_name]
+        cost = calc_trade_cost(row, scenario)
+        adjusted = row["pnl_bps"] - cost
+        assert adjusted == expected_adj, f"{scenario_name}: {adjusted} != {expected_adj}"
+
+
+# ── 회귀 테스트 ──────────────────────────────────────────────────
+
+
+def test_regression_fees_only_cum_pnl():
+    """18건 전체를 fees_only로 돌렸을 때 CumPnL == -173.9 bps (+-0.5 bps 허용)."""
+    jsonl_path = Path("data/trade_history/mtf_xrpusdtusdt.jsonl")
+    if not jsonl_path.exists():
+        pytest.skip("로컬 jsonl 파일 없음")
+
+    df = pd.read_json(jsonl_path, lines=True)
+    df["entry_ts"] = pd.to_datetime(df["entry_ts"], utc=True)
+    df["exit_ts"] = pd.to_datetime(df["exit_ts"], utc=True)
+    df["duration_min"] = (df["exit_ts"] - df["entry_ts"]).dt.total_seconds() / 60
+
+    result = apply_cost_model(df, "fees_only")
+    metrics = calc_metrics(result, pnl_col="adjusted_pnl_bps")
+
+    assert metrics["trades"] == 18
+    assert abs(metrics["cum_pnl"] - (-173.9)) <= 0.5, f"CumPnL={metrics['cum_pnl']}, expected -173.9"
+
+
+# ── calc_metrics 테스트 ──────────────────────────────────────────
+
+
+def test_calc_metrics_empty():
+    """빈 DataFrame -> 안전한 기본값."""
+    df = pd.DataFrame(columns=["pnl_bps", "duration_min"])
+    m = calc_metrics(df)
+    assert m["trades"] == 0
+    assert m["pf"] == 0.0
+
+
+def test_calc_metrics_with_avg_pnl():
+    """avg_pnl 필드가 정확히 계산되는지 확인."""
+    df = pd.DataFrame({
+        "pnl_bps": [10.0, -5.0, 20.0],
+        "duration_min": [60.0, 30.0, 90.0],
+    })
+    m = calc_metrics(df)
+    assert m["trades"] == 3
+    assert m["avg_pnl"] == pytest.approx(25.0 / 3, abs=0.01)
--- a/tests/test_mtf_bot.py
+++ b/tests/test_mtf_bot.py
@@ -421,3 +421,107 @@ class TestExecutionManager:
        # TP/SL = 2.3/1.5 = 1.533...
        expected_rr = round(2.3 / 1.5, 2)
        assert result["risk_reward"] == expected_rr
+
+
+# ═══════════════════════════════════════════════════════════════════
+# Test 5: ExecutionManager 킬스위치
+# ═══════════════════════════════════════════════════════════════════
+
+
+class TestExecutionManagerKillSwitch:
+    """ExecutionManager 킬스위치 (Fast Kill / Slow Kill) 테스트."""
+
+    def _make_em(self) -> ExecutionManager:
+        """JSONL 복원 없이 깨끗한 ExecutionManager 생성."""
+        em = ExecutionManager.__new__(ExecutionManager)
+        em.symbol = "TESTUSDT"
+        em.current_position = None
+        em._entry_price = None
+        em._entry_ts = None
+        em._sl_price = None
+        em._tp_price = None
+        em._atr_at_entry = None
+        em._killed = False
+        em._trade_history = []
+        return em
+
+    def test_fast_kill_triggers_after_8_consecutive_losses(self):
+        """8연속 손실 시 Fast Kill 발동."""
+        em = self._make_em()
+        for _ in range(8):
+            em._append_trade_history(-50.0)
+        assert em._check_kill_switch() is True
+        assert em._killed is True
+
+    def test_fast_kill_not_triggered_with_7_losses(self):
+        """7연속 손실은 Fast Kill 미발동."""
+        em = self._make_em()
+        for _ in range(7):
+            em._append_trade_history(-50.0)
+        assert em._check_kill_switch() is False
+        assert em._killed is False
+
+    def test_fast_kill_broken_by_single_win(self):
+        """연속 손실 중 1회 수익이 있으면 Fast Kill 미발동."""
+        em = self._make_em()
+        for _ in range(4):
+            em._append_trade_history(-50.0)
+        em._append_trade_history(10.0)  # 중간에 수익
+        for _ in range(3):
+            em._append_trade_history(-50.0)
+        assert em._check_kill_switch() is False
+
+    def test_slow_kill_triggers_when_pf_below_threshold(self):
+        """최근 15거래 PF < 0.75 시 Slow Kill 발동."""
+        em = self._make_em()
+        # 12패 (-100 bps each) + 3승 (+50 bps each)
+        # gross_profit=150, gross_loss=1200, PF=0.125
+        for _ in range(12):
+            em._append_trade_history(-100.0)
+        for _ in range(3):
+            em._append_trade_history(50.0)
+        assert em._check_kill_switch() is True
+        assert em._killed is True
+
+    def test_slow_kill_not_triggered_when_pf_above_threshold(self):
+        """PF > 0.75면 Slow Kill 미발동."""
+        em = self._make_em()
+        # 7패 (-100 each) + 8승 (+100 each)
+        # gross_profit=800, gross_loss=700, PF=1.14
+        for _ in range(7):
+            em._append_trade_history(-100.0)
+        for _ in range(8):
+            em._append_trade_history(100.0)
+        assert em._check_kill_switch() is False
+
+    def test_killed_state_blocks_new_entry(self):
+        """킬스위치 발동 후 신규 진입이 차단된다."""
+        em = self._make_em()
+        em._killed = True
+        result = em.execute("EXECUTE_LONG", 2.0, 0.01)
+        assert result is None
+
+    def test_killed_state_allows_existing_sl_tp(self):
+        """킬스위치 발동 후에도 기존 포지션의 청산은 정상 동작."""
+        em = self._make_em()
+        # 먼저 포지션 진입
+        em.execute("EXECUTE_SHORT", 2.0, 0.01)
+        # 킬스위치 발동
+        em._killed = True
+        # 청산은 정상 동작해야 함
+        em.close_position("SL 히트", exit_price=2.015, pnl_bps=-75.0)
+        assert em.current_position is None
+
+    def test_kill_switch_integrated_with_close(self):
+        """close_position 호출 시 자동으로 킬스위치 판정이 실행된다."""
+        em = self._make_em()
+        # 7번 손실 기록
+        for _ in range(7):
+            em._append_trade_history(-50.0)
+        # 포지션 진입 후 8번째 손실로 청산
+        em.execute("EXECUTE_SHORT", 2.0, 0.01)
+        em.close_position("SL 히트", exit_price=2.015, pnl_bps=-75.0)
+        # 8연패 → Fast Kill 발동
+        assert em._killed is True
+        # 다음 진입 차단
+        assert em.execute("EXECUTE_LONG", 1.95, 0.01) is None
Author	SHA1	Message	Date
21in7	09ae926f06	docs: 전략 post-mortem — 7전 7패 분석 및 다음 방향 제안 - 공통 실패 패턴 3가지 (IS/OOS 격차, 대칭성 실패, 필터 역효과) - 근본 원인: 공개 시그널 방향 예측 패러다임 한계 - 다음 방향: 패러다임 변경(stat arb), 비용 절감(maker), 데이터 확장 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-04 09:30:10 +09:00
21in7	f53b8a5a0f	research: MTF + BTC 추세 필터 백테스트 — FAIL, MTF 전략 최종 폐기 - 메인 가설(BTC 1h EMA50/200 ADX>20) OOS fees PF 0.90, 베이스라인(0.94)보다 악화 - 12개 sweep 조합 중 합격(fees PF>=1.2) 0개 - 761일 데이터로 전략 근본적 edge 부재 확인 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-04 09:24:45 +09:00
21in7	52d05f2ddd	feat: 전략 리서치 스크립트 및 테스트 일괄 추가 - FR/OI 백테스트, LS ratio 백테스트 스크립트 - 펀딩/OI 분석, 거래 LS 분석 스크립트 - evaluate_oos 테스트 추가 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-04 09:03:06 +09:00
21in7	4a7b38ea43	results: 백테스트 및 주간 리포트 결과 일괄 추가 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-04 09:03:03 +09:00
21in7	cc0838e854	docs: 전략 리서치 결과 문서 일괄 추가 - FR+OI 백테스트 결과 (폐기) - LS ratio 백테스트 설계/결과 (폐기) - Binance 공개 API 리서치 (edge 없음) - MTF 백테스트 및 OOS 중간 보고 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-04 09:03:02 +09:00
21in7	112f3e2377	models: DOGE/XRP/SOL 모델 및 학습 로그 업데이트 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-04 09:02:57 +09:00
21in7	960f997aac	data: 최신 15m 캔들 데이터 및 거래 기록 업데이트 - DOGE/TRX/XRP/BTC/ETH 15m parquet 데이터 갱신 - MTF dry-run 거래 기록 추가 - XRP LS ratio 데이터 추가 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-04 09:02:56 +09:00
21in7	98476cc972	feat: MTF bot kill switch 및 비용 모델 추가 - src/config.py: COST_MODEL, COST_SCENARIOS 비용 모델 상수 추가 - src/mtf_bot.py: bps 기반 kill switch (Fast Kill + Slow Kill) 구현 - tests/test_mtf_bot.py: kill switch 테스트 케이스 추가 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-04 09:02:51 +09:00
21in7	29e307d7b2	fix: evaluate_oos 판정 로직을 fees_only PF 기준으로 수정하고 MTF OOS 최종 결과 문서화 - 판정 기준을 Raw PF → fees_only PF로 변경 (Raw PF는 비현실적) - LONG/SHORT 대칭성 체크 추가 (양쪽 PF >= 0.8) - MTF OOS 최종 결과: FAIL 폐기 (30건, fees_only PF 0.84, SHORT PF 0.56) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-04 09:01:40 +09:00