LAB #448 NEUTRAL: LEDGER BENCH: Apply filter: Session = LONDON_OPEN — improves win rate from 32.4% to 32.9% (+0.5pp, n — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = LONDON_OPEN — improves win rate from 32.4% to 32.9% (+0.5pp, n=207) SAME-WINDOW EFFECT: Applying the LONDON_OPEN filter to the current trade window would have excluded the GBPUSD LONG via wkjudas (entry 1.34135, closed LOSS) and the USDJPY SHORT via wkjudas (entry 162.601, closed LOSS), as both were entered outside the London open session. This would have removed two losing trades, improving the window's win rate from 3 wins / 5 closed trades (60%) to 3 wins / 3 closed trades (100%), a +40pp gain. However, the sample is tiny (n=5 closed trades), so this is not statistically meaningful. The filter would not have affected the REJECTED/open trades, as they remain unresolved. OVER-TIME PROJECTION: Over 3-6 months, a +0.5pp win-rate improvement from n=207 backtests suggests a fragile edge that may not replicate in live trading due to session-specific noise and low signal strength. The risk is t Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com