LAB #2681 NEUTRAL: LEDGER BENCH: Apply filter: Session = LONDON_OPEN — improves win rate from 31.1% to 31.4% (+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 31.1% to 31.4% (+0.3pp, n=245) SAME-WINDOW EFFECT: Applying the LONDON_OPEN filter to the current 10-trade window would have excluded the two XAUUSD trades (entries at 10:10 and 11:20+ on different days) that fall outside the strict London session (typically 08:00–12:00 UTC, which is 10:00–14:00 CEST). The remaining 8 trades (all FX) show 5 wins and 3 losses — a 62.5% win rate vs. the current 60% (6/10). However, the filter would have removed the XAUUSD LONG win (a winner), so the net PnL delta is negative: you lose that profitable trade while keeping the same loss count. Expected win-rate improvement is marginal (+2.5pp on this tiny sample), but PnL would drop by roughly the size of that gold win (≈+$X per unit), making the filter counterproductive in this specific window. OVER-TIME PROJECTION: Over 3–6 months, the +0.3pp win-rate gain (31.1%→31.4%) is Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com