Add two new OI-derived features to improve ML model's market microstructure
understanding:
- oi_change_ma5: 5-candle moving average of OI change rate (short-term trend)
- oi_price_spread: z-scored OI minus z-scored price return (divergence signal)
Both features use 96-candle rolling z-score window. FEATURE_COLS expanded from
24 to 26. Existing tests updated to reflect new feature counts.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Added `ML_THRESHOLD` parameter to README, specifying its role in ML filter predictions.
- Included a new entry in the training log with detailed metrics from a recent model training session, enhancing performance tracking and documentation.
Migrate ADX from hard filter (ADX < 25 blocks entry) to ML feature so
the model can learn optimal ADX thresholds from data. Updates FEATURE_COLS,
build_features(), and corresponding tests from 23 to 24 features.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Log current price and unrealized PnL every 5 minutes while holding a position,
using the existing kline WebSocket's unclosed candle data for real-time price updates.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Added ML_THRESHOLD to .env.example and updated Config class to include ml_threshold with a default value of 0.55.
- Modified MLFilter initialization in bot.py to utilize the new ml_threshold configuration.
- Updated Jenkinsfile to change the registry URL for Docker image management.
These changes enhance the model's adaptability by allowing for a configurable machine learning threshold, improving overall performance.
- Introduced a new plan to modify the Optuna objective function to prioritize precision under a recall constraint of 0.35, improving model performance in scenarios where false positives are costly.
- Updated training scripts to implement precision-based metrics and adjusted the walk-forward cross-validation process to incorporate precision and recall calculations.
- Enhanced the active LGBM parameters and training log to reflect the new metrics and model configurations.
- Added a new design document outlining the implementation steps for the precision-focused optimization.
This update aims to refine the model's decision-making process by emphasizing precision, thereby reducing potential losses from false positives.
- Updated active LGBM parameters with new timestamp, trial results, and model configurations to reflect recent training outcomes.
- Added new entries to the training log, capturing detailed metrics including AUC, precision, recall, and tuned parameters for the latest model iterations.
This update enhances the tracking of model performance and parameter tuning in the ML pipeline.
Added HOLD candles as negative samples to increase training data from ~535 to ~3,200 samples. Introduced a negative_ratio parameter in generate_dataset_vectorized() for sampling HOLD candles alongside signal candles. Implemented stratified undersampling to ensure signal samples are preserved during training. Updated relevant tests to validate new functionality and maintain compatibility with existing tests.
- Modified dataset_builder.py to include HOLD negative sampling logic
- Updated train_model.py to apply stratified undersampling
- Added tests for new sampling methods
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The two HOLD negative tests (test_hold_negative_labels_are_all_zero,
test_signal_samples_preserved_after_sampling) were passing vacuously
because sample_df produces 0 signal candles (ADX ~18, below threshold
25). Added signal_producing_df fixture with higher volatility and volume
surges to reliably generate signals. Removed if-guards so assertions
are mandatory. Also restored the full docstring for
generate_dataset_vectorized() documenting btc_df/eth_df,
time_weight_decay, and negative_ratio parameters.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add negative_ratio parameter to generate_dataset_vectorized() that
samples HOLD candles as label=0 negatives alongside signal candles.
This increases training data from ~535 to ~3,200 samples when enabled.
- Split valid_rows into base_valid (shared) and sig_valid (signal-only)
- Add 'source' column ("signal" vs "hold_negative") for traceability
- HOLD samples get label=0 and random 50/50 side assignment
- Default negative_ratio=0 preserves backward compatibility
- Fix incorrect column count assertion in existing test
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Introduced CLAUDE.md to provide comprehensive guidance on the CoinTrader project, including architecture, common commands, testing, and deployment details. Added settings.json to enable the superpowers plugin for Claude. This enhances the project's documentation and configuration management.
ADX < 25 now returns HOLD in get_signal(), preventing entries during
trendless (sideways) markets. NaN ADX values fall through to existing
weighted signal logic. Also syncs the vectorized dataset builder with
the same ADX filter to keep training data consistent.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add ADX (Average Directional Index) with period 14 to calculate_all()
for sideways market filtering. Includes test verifying the adx column
exists and contains non-negative values.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Added a new entry to the training log with detailed metrics for a LightGBM model, including AUC, precision, recall, and tuned parameters.
- Enhanced the MLFilter class to include a guard clause that prevents execution if the filter is disabled, improving robustness.
- Introduced a comprehensive architecture document detailing the CoinTrader system, including an overview, core layer architecture, MLOps pipeline, and key operational scenarios.
- Updated README to reference the new architecture document and added a configuration option to disable the ML filter.
- Enhanced the ML filter to allow for complete signal acceptance when the NO_ML_FILTER environment variable is set.
- Updated the README to clarify the listenKey auto-renewal mechanism, including the use of `stream.recv()` for message reception.
- Added information on immediate reconnection upon detecting internal error payloads to prevent zombie connections.
- Introduced User Data Stream to detect TP/SL executions in real-time.
- Added a new class `UserDataStream` for managing the stream and handling events.
- Updated `bot.py` to initialize and run the User Data Stream in parallel with the candle stream.
- Enhanced `notifier.py` to send detailed Discord notifications including estimated vs actual PnL.
- Added methods in `exchange.py` for managing listenKey lifecycle (create, keepalive, delete).
- Refactored PnL recording and notification logic to streamline handling of position closures.
Made-with: Cursor
- __init__에 _entry_price, _entry_quantity 상태 변수 추가 (None 초기화)
- _open_position()에서 current_trade_side 저장 직후 진입가/수량 저장
- _calc_estimated_pnl() 헬퍼: LONG/SHORT 방향별 예상 PnL 계산
- _on_position_closed() 콜백: UDS 청산 감지 시 PnL 기록·알림·상태 초기화
Made-with: Cursor
- Updated timestamp and elapsed seconds in models/active_lgbm_params.json.
- Adjusted baseline AUC and fold AUCs to reflect new model performance.
- Added a new entry in models/training_log.json with detailed metrics from the latest training run, including tuned parameters and model path.
Made-with: Cursor
- tune_hyperparams.py: 탐색 완료 후 Best AUC > Baseline AUC 이면
models/active_lgbm_params.json 자동 갱신
- tune_hyperparams.py: 베이스라인을 active 파일 기준으로 측정
(active 없으면 코드 내 기본값 사용)
- train_model.py: _load_lgbm_params()에 active 파일 자동 탐색 추가
우선순위: --tuned-params > active_lgbm_params.json > 하드코딩 기본값
- models/active_lgbm_params.json: 현재 best 파라미터로 초기화
- .gitignore: tune_results_*.json 제외, active 파일은 git 추적 유지
Made-with: Cursor
- scripts/tune_hyperparams.py: Optuna + Walk-Forward 5폴드 AUC 목적 함수
- 데이터셋 1회 캐싱으로 모든 trial 공유 (속도 최적화)
- num_leaves <= 2^max_depth - 1 제약 강제 (소규모 데이터 과적합 방지)
- MedianPruner로 저성능 trial 조기 종료
- 결과: 콘솔 리포트 + models/tune_results_YYYYMMDD_HHMMSS.json
- requirements.txt: optuna>=3.6.0 추가
- README.md: 하이퍼파라미터 자동 튜닝 사용법 섹션 추가
- docs/plans/: 설계 문서 및 구현 플랜 추가
Made-with: Cursor
- Added `--upsert` flag to `fetch_history.py` for merging new data into existing parquet files.
- Implemented `upsert_parquet()` function to update existing rows with new values where `oi_change` and `funding_rate` are 0.0, while appending new rows.
- Created tests in `tests/test_fetch_history.py` to validate upsert behavior.
- Updated `.gitignore` to include `.cursor/` directory.
Made-with: Cursor
