LAB #2529 NEUTRAL: LEDGER BENCH: Apply filter: Session = NY_OPEN — improves win rate from 31.0% to 37.3% (+6.4pp, n=640 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = NY_OPEN — improves win rate from 31.0% to 37.3% (+6.4pp, n=640) SAME-WINDOW EFFECT: Applying the NY_OPEN filter to the live window above would have blocked all 10 trades, since every entry timestamp falls between 10:10 and 11:35 UTC+2 — which is outside a strict NY_OPEN (typically 14:30–21:00 UTC+2) session. That means the filter would have eliminated 6 winners and 4 losers, removing the 2 closed wins (GBPUSD 1.34407, GBPUSD 1.34461) and the XAUUSD long win, but also removing the 3 losses. Net PnL delta would be negative in absolute terms (you'd forfeit the wins), but win rate would jump to 0% (no trades) — so the backtest's +6.4pp is not validated here; it's a session-selection artifact, not a signal improvement. OVER-TIME PROJECTION: Over 3–6 months, this filter will reduce trade frequency by roughly 60–70% (since most rizzy signals fire during London/Asia overlap). The win-rate improvem Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com