LAB #2320 NEUTRAL: LEDGER BENCH: Apply filter: Session = LONDON_OPEN — improves win rate from 31.5% to 31.8% (+0.3pp, n — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = LONDON_OPEN — improves win rate from 31.5% to 31.8% (+0.3pp, n=239) SAME-WINDOW EFFECT: Applying the LONDON_OPEN filter to the current live window would have excluded the EURJPY LONG (18:00 entry) and likely the GBPUSD SHORT (11:00 entry is borderline, depending on your exact session definition). The remaining trades (XAUUSD, AUDUSD, USDCAD, USDJPY, EURJPY SHORTs) are mostly within the London session, so the filter would not have changed their outcomes. The net effect is negligible: you'd drop one WIN (EURJPY LONG) and possibly one LOSS (GBPUSD), leaving win rate roughly flat. Expected PnL delta: approximately -0.2% to +0.1% — statistically indistinguishable from noise. OVER-TIME PROJECTION: Over 3-6 months, a +0.3pp win-rate improvement on a 31.5% base is within the 95% confidence interval of random variation (standard error ≈ 3.1% for n=239). The filter may reduce trade frequency by ~15- Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com