21in7 8dd1389b16 feat: add Optuna Walk-Forward AUC hyperparameter tuning pipeline ...

- 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

2026-03-02 14:39:07 +09:00

..

2026-03-01-15m-timeframe-upgrade.md

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

2026-03-01 22:16:15 +09:00

2026-03-01-btc-eth-correlation-features-design.md

feat: implement BTC/ETH correlation features for improved model accuracy

2026-03-01 19:30:17 +09:00

2026-03-01-btc-eth-correlation-features-plan.md

feat: implement BTC/ETH correlation features for improved model accuracy

2026-03-01 19:30:17 +09:00

2026-03-01-discord-notifier-and-position-recovery.md

feat: Discord 알림, 포지션 복구, 설정 개선 및 docs 추가

2026-03-01 15:57:08 +09:00

2026-03-01-dockerfile-and-docker-compose.md

feat: implement ML filter with LightGBM for trading signal validation

2026-03-01 17:07:18 +09:00

2026-03-01-dynamic-margin-ratio-design.md

chore: remove unused risk_per_trade references

2026-03-01 20:39:26 +09:00

2026-03-01-dynamic-margin-ratio-plan.md

chore: remove unused risk_per_trade references

2026-03-01 20:39:26 +09:00

2026-03-01-fix-pandas-ta-python312.md

feat: implement ML filter with LightGBM for trading signal validation

2026-03-01 17:07:18 +09:00

2026-03-01-jenkins-gitea-registry-cicd.md

feat: implement ML filter with LightGBM for trading signal validation

2026-03-01 17:07:18 +09:00

2026-03-01-lgbm-improvement.md

feat: implement LightGBM model improvement plan with feature normalization and walk-forward validation

2026-03-01 22:02:32 +09:00

2026-03-01-m4-accelerated-training.md

feat: implement training and deployment pipeline for LightGBM model on Mac to LXC

2026-03-01 18:30:01 +09:00

2026-03-01-ml-filter-design.md

feat: implement ML filter with LightGBM for trading signal validation

2026-03-01 17:07:18 +09:00

2026-03-01-ml-filter-implementation.md

feat: implement ML filter with LightGBM for trading signal validation

2026-03-01 17:07:18 +09:00

2026-03-01-oi-nan-epsilon-precision-threshold.md

chore: .worktrees/ gitignore에 추가

2026-03-01 23:50:18 +09:00

2026-03-01-train-on-mac-deploy-to-lxc.md

feat: implement training and deployment pipeline for LightGBM model on Mac to LXC

2026-03-01 18:30:01 +09:00

2026-03-01-upload-to-gitea.md

feat: Discord 알림, 포지션 복구, 설정 개선 및 docs 추가

2026-03-01 15:57:08 +09:00

2026-03-01-vectorized-dataset-builder.md

feat: remove in-container retraining, training is now mac-only

2026-03-01 18:54:00 +09:00

2026-03-01-xrp-futures-autotrader.md

feat: Discord 알림, 포지션 복구, 설정 개선 및 docs 추가

2026-03-01 15:57:08 +09:00

2026-03-02-oi-funding-accumulation.md

feat: implement upsert functionality in fetch_history.py to accumulate OI/funding data

2026-03-02 14:16:09 +09:00

2026-03-02-optuna-hyperparam-tuning-design.md

feat: add Optuna Walk-Forward AUC hyperparameter tuning pipeline

2026-03-02 14:39:07 +09:00

2026-03-02-optuna-hyperparam-tuning-plan.md

feat: add Optuna Walk-Forward AUC hyperparameter tuning pipeline

2026-03-02 14:39:07 +09:00

2026-03-02-realtime-oi-funding-features.md

feat: implement upsert functionality in fetch_history.py to accumulate OI/funding data

2026-03-02 14:16:09 +09:00

2026-03-02-reverse-signal-reenter-design.md

feat: implement immediate re-entry after closing position on reverse signal

2026-03-02 01:34:36 +09:00

2026-03-02-reverse-signal-reenter-plan.md

feat: implement immediate re-entry after closing position on reverse signal

2026-03-02 01:34:36 +09:00

2026-03-02-rs-divide-mlx-nan-fix.md

chore: .gitignore에 .DS_Store 추가 및 MLXFilter 훈련 로그 업데이트

2026-03-02 00:41:34 +09:00