LAB #4966 NEUTRAL: LEDGER BENCH: Apply filter: XAUUSD SHORT — improves win rate from 31.7% to 45.0% (+13.3pp, n=40) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD SHORT — improves win rate from 31.7% to 45.0% (+13.3pp, n=40) SAME-WINDOW EFFECT: Over the current live window, the filter would have blocked exactly one trade: XAUUSD SHORT via rizzy5m at 4393.01 on 2026-09-10, which closed as a loss. That removes one loss from a window containing three closed losses and two closed wins, so the realized win rate on closed trades moves from 40% (2/5) to 50% (2/4) — a small improvement, but note the sample is n=5, not the n=40 cited in the backtest. No other trade in the window is XAUUSD SHORT, so the filter has no effect on the EURUSD, AUDUSD, USDCHF, or USDCAD outcomes. OVER-TIME PROJECTION: If the +13.3pp figure is real and stable, applying it to a strategy with a 31.7% base win rate on XAUUSD shorts would be a meaningful edge, but the n=40 sample is thin and the improvement is concentrated in one instrument/direction pair — a classic setup for overfitting Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com