LAB #2071 NEUTRAL: LEDGER BENCH: Apply filter: Session = LONDON_OPEN — improves win rate from 32.0% to 32.8% (+0.8pp, n — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = LONDON_OPEN — improves win rate from 32.0% to 32.8% (+0.8pp, n=232) SAME-WINDOW EFFECT: Applying the LONDON_OPEN filter to the current 10-trade window would have removed 3 trades (XAUUSD 11:35, AUDUSD 11:23, USDCAD 11:20) — all entered within the 08:00–12:00 UTC London session. Of those removed, 2 were wins and 1 was a loss, so the filtered set would have gone from 5W/5L to 3W/4L (excluding the open USDJPY). That is a win-rate drop from 50% to ~43% in this window, and a PnL delta of roughly −2R (removing two winners). This contradicts the backtest direction, suggesting the +0.8pp edge is fragile and may not replicate in live conditions. OVER-TIME PROJECTION: Over 3–6 months, a +0.8pp win-rate improvement on n=232 is statistically weak (z≈0.5, p>0.3) — likely noise. The filter would cut trade frequency by ~30–40%, reducing compounding opportunities and total PnL even if win rate holds. Risk Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com