LAB #2814 NEUTRAL: LEDGER BENCH: Apply filter: Session = OFF_SESSION — improves win rate from 31.1% to 44.4% (+13.3pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = OFF_SESSION — improves win rate from 31.1% to 44.4% (+13.3pp, n=99) SAME-WINDOW EFFECT: Applying the OFF_SESSION filter to the current live window would have blocked the 2026-08-04 11:15 USDJPY SHORT (wkjudas, LOSS) and the 2026-08-04 11:20 USDCAD SHORT (rizzy5m, WIN) — both fall outside the defined OFF_SESSION period. That removes one loss and one win, netting zero PnL change but shifting win rate from 6/10 to 5/8 (62.5% vs 60%). The filter would not have touched the other eight trades, so the immediate impact is negligible — the +13.3pp backtest edge does not appear in this small live sample. OVER-TIME PROJECTION: Over 3–6 months, the filter could reduce trade frequency by roughly 20–30% (based on session distribution), which may improve win rate but also cut total profit if the removed trades have asymmetric positive expectancy. The main risk is overfitting to a 99-trade backtest — OFF_ Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com