LAB #2801 NEUTRAL: LEDGER BENCH: Apply filter: Session = NY_OPEN — improves win rate from 31.0% to 37.1% (+6.2pp, n=644 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = NY_OPEN — improves win rate from 31.0% to 37.1% (+6.2pp, n=644) SAME-WINDOW EFFECT: Applying the NY_OPEN filter to the current live window would have removed the 10:10 and 11:35 entries (both GBPUSD wins) and the 10:10 XAUUSD long (win), but kept the 11:20 USDCAD short (win) and 11:23 AUDUSD long (win). Net effect: 3 wins removed, 0 losses removed → win rate drops from 6/10 to 3/7 (42.9% → 42.9% flat), but total PnL would decrease by roughly +3R (assuming ~1R per win). The filter would have hurt this specific window, not helped it. OVER-TIME PROJECTION: The backtest claims +6.2pp on n=644, but that is a single-session slice with likely regime dependence. Over 3–6 months, NY_OPEN-only trading reduces opportunity count by ~60–70%, which may lower total PnL even if win rate improves. Risk: the filter may be overfit to recent volatility clustering (e.g., London/NY overlap news spikes); if vola Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com