LAB #4004 NEUTRAL: LEDGER BENCH: Apply filter: Session = NY_OPEN — improves win rate from 32.5% to 39.0% (+6.5pp, n=772 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = NY_OPEN — improves win rate from 32.5% to 39.0% (+6.5pp, n=772) SAME-WINDOW EFFECT: Applying the NY_OPEN filter would have excluded every trade in the current live window, since all 10 entries occurred between 02:43 and 11:35 UTC+2 — none fall within a typical NY session (13:30–20:00 UTC+2). That means 0 of the 3 wins (GBPUSD, EURUSD) and 0 of the 5 losses would have been taken, eliminating both the +2 wins and the -3 losses. Net PnL delta would be roughly neutral to slightly positive (avoiding the 3 losses outweighs missing the 2 wins, but you also lose the open NZDUSD positions). The apparent +6.5pp win-rate gain is not validated here — it's a zero-trade outcome, so no real signal. OVER-TIME PROJECTION: Over 3–6 months, the filter would drastically reduce trade frequency (likely 60–80% fewer trades), which can inflate win rate via survivorship bias while cutting total PnL. The risk is th Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com