Commit Graph
2 Commits
Author SHA1 Message Date
gavindiazandClaude Code 1bcfe6e374 feat(research): complete the offline pipeline and add live-identical backtest
research/ now runs end-to-end (fetch -> features/labels -> walk-forward ->
train -> OOS evaluate -> save), and backtest_strategy() replays the same
signal(ctx) strategy over a historical frame with the same manage_position
hook the live loop calls, simulating SL/TP, trailing, partial closes and cost
per bar. --backtest wires it into the CLI.

Co-Authored-By: Claude Code <noreply@anthropic.com>
2026-10-25 20:20:49 +08:00
gavindiazandClaude Code ddaeb6685f feat(research): add offline research pipeline skeleton
Data -> storage (parquet/CSV) -> features/labels -> walk-forward
(strategy_validate) -> train -> evaluate, driving mtdata-cli as a
subprocess. Binary P(+1) target from triple-barrier labels; sklearn
models (optional lightgbm) persisted via ModelWrapper for the trading/
execution shell's signal(ctx) interface.

Co-Authored-By: Claude Code <noreply@anthropic.com>
2026-10-22 21:07:42 +08:00