21in7 30ddb2fef4 feat(ml): relax training thresholds for 5-10x more training samples ...

Add TRAIN_* constants (signal_threshold=2, adx=15, vol_mult=1.5, neg_ratio=3)
as dataset_builder defaults. Remove hardcoded negative_ratio=5 from all callers.
Bot entry conditions unchanged (config.py strict values).

WF 5-fold results (all symbols AUC 0.91+):
- XRPUSDT: 0.9216 ± 0.0052
- SOLUSDT:  0.9174 ± 0.0063
- DOGEUSDT: 0.9222 ± 0.0085

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-03-21 19:38:15 +09:00

..

__init__.py

feat: implement ML filter with LightGBM for trading signal validation

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

collect_oi.py

feat: add OI long-term collection script for cron-based data accumulation

2026-03-04 20:24:14 +09:00

compare_symbols.py

feat: add symbol comparison and position sizing analysis tools

2026-03-18 23:35:42 +09:00

deploy_model.sh

feat: add --symbol/--all CLI to all training scripts for per-symbol pipeline

2026-03-05 23:21:32 +09:00

fetch_history.py

fix: add retry with exponential backoff to OI/funding API calls (#4)

2026-03-07 16:00:52 +09:00

position_sizing_analysis.py

feat: add symbol comparison and position sizing analysis tools

2026-03-18 23:35:42 +09:00

profile_training.py

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

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

run_backtest.py

feat: strategy parameter sweep and production param optimization

2026-03-06 23:39:43 +09:00

run_optuna.sh

feat: add run_optuna.sh wrapper script for Optuna tuning

2026-03-02 14:50:50 +09:00

run_tests.sh

feat: implement HOLD negative sampling and stratified undersampling in ML pipeline

2026-03-03 00:13:42 +09:00

strategy_sweep.py

feat: strategy parameter sweep and production param optimization

2026-03-06 23:39:43 +09:00

test_reverse_reenter.sh

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

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

train_and_deploy.sh

feat: enhance data handling and model training features

2026-03-05 23:57:44 +09:00

train_mlx_model.py

feat(ml): relax training thresholds for 5-10x more training samples

2026-03-21 19:38:15 +09:00

train_model.py

feat(ml): relax training thresholds for 5-10x more training samples

2026-03-21 19:38:15 +09:00

tune_hyperparams.py

feat(ml): relax training thresholds for 5-10x more training samples

2026-03-21 19:38:15 +09:00

weekly_report.py

feat(weekly-report): add kill switch monitoring section

2026-03-18 23:58:22 +09:00