LAB #4135 NEUTRAL: LEDGER BENCH: Apply filter: Session = NY_OPEN — improves win rate from 32.6% to 39.0% (+6.4pp, n=782 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = NY_OPEN — improves win rate from 32.6% to 39.0% (+6.4pp, n=782) SAME-WINDOW EFFECT: Applying the NY_OPEN filter to the live window above would have excluded all trades timestamped outside the NY session (roughly 14:00–21:00 UTC, or 16:00–23:00 SAST). In the listed window, only the GBPUSD SHORT at 11:50 SAST (09:50 UTC) and the AUDUSD SHORT at 11:35 SAST fall inside NY_OPEN; the rest (10:20, 10:15, 15:08, 14:36, 02:43, 09:25, 09:15, 11:05 SAST) are outside. Of the two retained trades, one is OPEN and one is REJECTED — meaning zero closed outcomes survive the filter. The backtest's +6.4pp win-rate gain does not translate here; the live window shows no closed trades to evaluate, so the immediate PnL delta is indeterminate but likely negligible or negative due to reduced trade count. OVER-TIME PROJECTION: Over 3–6 months, restricting to NY_OPEN will cut trade frequency substantially (likely 50 Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com