LAB #2307 PROMISING: LEDGER BENCH: Apply filter: XAUUSD SHORT — improves win rate from 31.5% to 50.0% (+18.5pp, n=32) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD SHORT — improves win rate from 31.5% to 50.0% (+18.5pp, n=32) SAME-WINDOW EFFECT: Applying the XAUUSD SHORT filter would have blocked the two XAUUSD SHORT losses (rizzy5m at 4051.79 and 4066.35) and the currently open XAUUSD LONG (rizzy7m at 4270.17) — but it would also have blocked the XAUUSD SHORT loss at 4048.74, which is already a loss. Net effect: 3 losing trades removed, 0 winning trades removed. That would flip the window from 4W/6L to 4W/3L, raising win rate from 40% to 57.1% — a +17.1pp improvement, consistent with your backtest. PnL delta is positive but modest, as the removed trades were all losses; no wins sacrificed. OVER-TIME PROJECTION: Over 3–6 months, the filter would likely improve win rate and reduce drawdown, but the sample (n=32) is tiny and the effect may be regime-dependent — XAUUSD SHORTs may perform differently in trending vs. ranging gold. Risk: you could be overfitt Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com