LAB #1835 NEUTRAL: LEDGER BENCH: Apply filter: XAUUSD SHORT @ NY_OPEN with 6 conf — improves win rate from 31.9% to 80. — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD SHORT @ NY_OPEN with 6 conf — improves win rate from 31.9% to 80.0% (+48.1pp, n=5) SAME-WINDOW EFFECT: Over the current live window, the filter would have blocked the two XAUUSD SHORT rizzy5m entries (4051.79 and 4066.35) — both closed as losses. That removes 2 losing trades from the 10 listed, shifting the window from 5W/5L to 5W/3L (62.5% win rate vs. 50%). PnL delta is positive but modest: you avoid two losses, but you also forfeit any potential future XAUUSD SHORT opportunities in the same session — net effect likely +0.5R to +1.0R on this small sample. OVER-TIME PROJECTION: Over 3–6 months, the filter claims a massive jump from 31.9% to 80% win rate, but that is based on n=5 — statistically meaningless. The real risk is overfitting to a tiny cluster of NY_OPEN XAUUSD SHORTs that happened to align with a specific volatility regime (likely high-conviction momentum). If the filter is too na Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com