feat: implement 15-minute timeframe upgrade for model training and data processing

- Introduced a new markdown document detailing the plan to transition the entire pipeline from a 1-minute to a 15-minute timeframe, aiming to improve model AUC from 0.49-0.50 to over 0.53.
- Updated key parameters across multiple scripts, including `LOOKAHEAD` adjustments and default data paths to reflect the new 15-minute interval.
- Modified data fetching and training scripts to ensure compatibility with the new timeframe, including changes in `fetch_history.py`, `train_model.py`, and `train_and_deploy.sh`.
- Enhanced the bot's data stream configuration to operate on a 15-minute interval, ensuring real-time data processing aligns with the new model training strategy.
- Updated training logs to capture new model performance metrics under the revised timeframe.

src/bot.py

@@ -20,7 +20,7 @@ class TradingBot:
         self.current_trade_side: str | None = None  # "LONG" | "SHORT"
         self.stream = MultiSymbolStream(
             symbols=[config.symbol, "BTCUSDT", "ETHUSDT"],
-            interval="1m",
+            interval="15m",
             on_candle=self._on_candle_closed,
         )
 

src/data_stream.py

@@ -5,13 +5,21 @@ import pandas as pd
 from binance import AsyncClient, BinanceSocketManager
 from loguru import logger
 
+# 15분봉 기준 EMA50 안정화에 필요한 최소 캔들 수.
+# EMA50=50, StochRSI(14,14,3,3)=44, MACD(12,26,9)=33 중 최댓값에 여유분 추가.
+_MIN_CANDLES_FOR_SIGNAL = 100
+
+# 초기 구동 시 REST API로 가져올 과거 캔들 수.
+# 15분봉 200개 = 50시간치 — EMA50(12.5h) 대비 4배 여유.
+_PRELOAD_LIMIT = 200
+
 
 
 class KlineStream:
     def __init__(
         self,
         symbol: str,
-        interval: str = "1m",
+        interval: str = "15m",
         buffer_size: int = 200,
         on_candle: Callable = None,
     ):
@@ -40,13 +48,13 @@ class KlineStream:
                 self.on_candle(candle)
 
     def get_dataframe(self) -> pd.DataFrame | None:
-        if len(self.buffer) < 50:
+        if len(self.buffer) < _MIN_CANDLES_FOR_SIGNAL:
             return None
         df = pd.DataFrame(list(self.buffer))
         df.set_index("timestamp", inplace=True)
         return df
 
-    async def _preload_history(self, client: AsyncClient, limit: int = 200):
+    async def _preload_history(self, client: AsyncClient, limit: int = _PRELOAD_LIMIT):
         """REST API로 과거 캔들 데이터를 버퍼에 미리 채운다."""
         logger.info(f"과거 캔들 {limit}개 로드 중...")
         klines = await client.futures_klines(
@@ -96,7 +104,7 @@ class MultiSymbolStream:
     def __init__(
         self,
         symbols: list[str],
-        interval: str = "1m",
+        interval: str = "15m",
         buffer_size: int = 200,
         on_candle: Callable = None,
     ):
@@ -142,13 +150,13 @@ class MultiSymbolStream:
     def get_dataframe(self, symbol: str) -> pd.DataFrame | None:
         key = symbol.lower()
         buf = self.buffers.get(key)
-        if buf is None or len(buf) < 50:
+        if buf is None or len(buf) < _MIN_CANDLES_FOR_SIGNAL:
             return None
         df = pd.DataFrame(list(buf))
         df.set_index("timestamp", inplace=True)
         return df
 
-    async def _preload_history(self, client: AsyncClient, limit: int = 200):
+    async def _preload_history(self, client: AsyncClient, limit: int = _PRELOAD_LIMIT):
         """REST API로 모든 심볼의 과거 캔들을 버퍼에 미리 채운다."""
         for symbol in self.symbols:
             logger.info(f"{symbol.upper()} 과거 캔들 {limit}개 로드 중...")

src/dataset_builder.py

@@ -11,10 +11,10 @@ import pandas_ta as ta
 
 from src.ml_features import FEATURE_COLS
 
-LOOKAHEAD    = 90
+LOOKAHEAD    = 24   # 15분봉 × 24 = 6시간 뷰
 ATR_SL_MULT  = 1.5
 ATR_TP_MULT  = 2.0
-WARMUP       = 60   # 지표 안정화에 필요한 최소 행 수
+WARMUP       = 60   # 15분봉 기준 60캔들 = 15시간 (지표 안정화 충분)
 
 
 def _calc_indicators(df: pd.DataFrame) -> pd.DataFrame:

src/ml_filter.py

@@ -44,6 +44,11 @@ class MLFilter:
         self._try_load()
 
     def _try_load(self):
+        # 로드 여부와 무관하게 두 파일의 현재 mtime을 항상 기록한다.
+        # 이렇게 해야 로드하지 않은 쪽 파일이 나중에 변경됐을 때만 리로드가 트리거된다.
+        self._loaded_onnx_mtime = _mtime(self._onnx_path)
+        self._loaded_lgbm_mtime = _mtime(self._lgbm_path)
+
         # ONNX 우선 시도
         if self._onnx_path.exists():
             try:
@@ -53,8 +58,6 @@ class MLFilter:
                     providers=["CPUExecutionProvider"],
                 )
                 self._lgbm_model = None
-                self._loaded_onnx_mtime = _mtime(self._onnx_path)
-                self._loaded_lgbm_mtime = 0.0
                 logger.info(
                     f"ML 필터 로드: ONNX ({self._onnx_path}) "
                     f"| 임계값={self._threshold}"
@@ -68,8 +71,6 @@ class MLFilter:
         if self._lgbm_path.exists():
             try:
                 self._lgbm_model = joblib.load(self._lgbm_path)
-                self._loaded_lgbm_mtime = _mtime(self._lgbm_path)
-                self._loaded_onnx_mtime = 0.0
                 logger.info(
                     f"ML 필터 로드: LightGBM ({self._lgbm_path}) "
                     f"| 임계값={self._threshold}"