LAB #4463 NEUTRAL: LEDGER BENCH: Apply filter: Session = NY_OPEN — improves win rate from 31.5% to 38.3% (+6.8pp, n=801 — 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=801) SAME-WINDOW EFFECT: Applying the NY_OPEN filter to the live window above would have excluded all 10 trades, as every entry timestamp falls outside the NY session (all are between 02:43 and 15:08 CET, which maps to pre-NY or late-NY/Asia/London hours). The 4 closed wins and 2 closed losses would vanish, leaving only the 2 rejected/open and 2 closed-loss trades that were already outside the filter — net effect: zero live PnL from this window, but also zero drawdown. The backtest's +6.8pp win-rate gain is not observable here because the sample is too small and misaligned; the filter would have prevented all activity, not improved selectivity. OVER-TIME PROJECTION: Over 3-6 months, this filter would drastically cut trade frequency — likely by 70-80% given your current entry times — while concentrating only on a narrow 2-3 hour win Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com