TPTBusiness 772ba6b722 feat: Add P5 ML Training Pipeline with LightGBM and 46 tests ...

- MLTrainer class with feature matrix builder from top factors by IC
- LightGBM training with time-series split (80/20) and early stopping
- Feature importance analysis (gain-based) with ranking
- Model persistence: model.txt + metadata.json + feature_importance.json + CSV
- Feedback generation for factor generation loop
- Model loading from disk
- Full pipeline: load factors -> train -> save -> generate feedback
- 46 unit tests covering all features
- lightgbm and scipy added to requirements.txt

2026-04-09 09:46:56 +02:00

..

backtesting

feat: Add Trading Protection System with 4 protections + comprehensive tests

2026-04-03 13:01:56 +02:00

finetune

fix: Remove clear-text storage of API key (CodeQL alert #8)

2026-04-02 23:08:11 +02:00

integration

feat: CLI Commands for strategy generation (P4 complete)

2026-04-09 09:28:24 +02:00

local

feat: Add P5 ML Training Pipeline with LightGBM and 46 tests

2026-04-09 09:46:56 +02:00

notebook

fix: model/factor experiment filtering in Qlib proposals (#1257)

2025-10-10 22:49:46 +08:00

oai

feat: add LLM-finetune scenario (#1314)

2026-03-02 19:04:10 +08:00

qlib

fix: Ensure backtest results save to DB and JSON files

2026-04-03 15:46:52 +02:00

rl

feat: Add RL Trading Agent system with 99 tests

2026-04-03 13:26:10 +02:00

utils

feat(rl): add AutoRL-Bench framework and benchmark integrations (#1348)

2026-03-17 15:49:30 +08:00