LAB #1828 NEUTRAL: LEDGER BENCH: Apply filter: XAUUSD LONG @ NY_OPEN with 5 conf — improves win rate from 31.9% to 76.2 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD LONG @ NY_OPEN with 5 conf — improves win rate from 31.9% to 76.2% (+44.2pp, n=21) SAME-WINDOW EFFECT: Over the current live window, the filter would have blocked the two XAUUSD SHORT losses (rizzy5m entries at 4051.79 and 4066.35) since it only allows LONG XAUUSD at NY_OPEN with 5 conf. That removes 2 losses from the 10-trade sample, shifting the live win rate from 5/10 (50%) to 5/8 (62.5%) — a modest improvement, but not the +44pp claimed in the backtest. The EURJPY and GBPUSD trades are unaffected, so the PnL delta is roughly +2R (assuming each loss was ~1R), but the sample is too small to validate the filter's edge. OVER-TIME PROJECTION: Over 3-6 months, this filter will drastically reduce XAUUSD trade frequency — likely from dozens to a handful per month — because it requires a specific time (NY_OPEN) and high confidence (5). The backtest's 76.2% win rate on n=21 is statistically fragile Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com