TPTBusiness 78fb607dbe fix(factors): detect and correct look-ahead bias in daily-constant factors ...

Daily factors (e.g. daily_log_return) carried same-day close data at 00:00,
giving the model end-of-day information at bar open — a classic look-ahead bias
that produced spurious IC=0.25 and Sharpe=24 with 98% win rate.

Changes:
- factor_runner.py: add _shift_daily_constant_factor_if_needed() that detects
  factors where >90% of days have a single unique intraday value, then shifts
  them by 1 trading day before IC computation
- prompts.yaml: add rule #7 instructing LLM to always shift(1) daily aggregates
  before forward-filling to minute bars

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-04-24 09:34:06 +02:00

..

app

feat: unified backtest engine, LLM error handling, strategy refactor

2026-04-17 22:52:07 +02:00

components

fix(security): resolve all 30 Bandit security alerts (B301, B614, B104)

2026-04-21 22:24:57 +02:00

core

feat: unified backtest engine, LLM error handling, strategy refactor

2026-04-17 22:52:07 +02:00

log

feat(logging): write complete LLM prompts and responses to daily JSONL log

2026-04-17 21:46:28 +02:00

oai

feat(logging): write complete LLM prompts and responses to daily JSONL log

2026-04-17 21:46:28 +02:00

scenarios

fix(factors): detect and correct look-ahead bias in daily-constant factors

2026-04-24 09:34:06 +02:00

utils

fix(security): Patch 5 CodeQL path injection and weak hashing alerts (#25-#30)

2026-04-11 21:54:27 +02:00