LAB #4487 NEUTRAL: LEDGER BENCH: Apply filter: Session = NY_OPEN — improves win rate from 31.5% to 38.3% (+6.8pp, n=802 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = NY_OPEN — improves win rate from 31.5% to 38.3% (+6.8pp, n=802) SAME-WINDOW EFFECT: Applying the NY_OPEN filter to the current live window would have excluded all 10 listed trades, as none carry timestamps within the NY_OPEN session (all entries fall between 02:43 and 15:08 +02:00, which spans Asian/European hours, not NY open). This means zero trades would have fired, eliminating the 4 wins, 3 losses, and 3 open/rejected positions. Net PnL delta would be roughly flat-to-negative in the short term, since the live window shows 4 wins vs 3 losses (excluding opens), but the filter would have removed all activity — a 100% trade reduction. The +6.8pp win-rate improvement in backtest does not translate here because the filter is too restrictive for the current trade cadence. OVER-TIME PROJECTION: Over 3-6 months, a strict NY_OPEN-only filter would drastically cut trade frequency — likely by 70-9 Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com