LAB #2669 PROMISING: LEDGER BENCH: Apply filter: XAUUSD SHORT — improves win rate from 31.1% to 48.5% (+17.4pp, n=33) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD SHORT — improves win rate from 31.1% to 48.5% (+17.4pp, n=33) SAME-WINDOW EFFECT: Applying the XAUUSD SHORT filter would have removed the two XAUUSD SHORT trades in the window (both losses: 4048.74 and 4051.79). It would not have touched the XAUUSD LONG win (4270.17), so the net effect is removing 2 losses from the 10-trade sample. That shifts the window win rate from 6/10 (60%) to 6/8 (75%), and PnL improves by the sum of those two losses — roughly +2R to +3R depending on stop distances. However, the sample is tiny and the filter is direction-specific, not signal-quality-specific, so the improvement is mostly removing a losing subset, not proving the filter adds edge elsewhere. OVER-TIME PROJECTION: Over 3–6 months, this filter would eliminate all XAUUSD short entries, which historically have a 31.1% win rate in your backtest (n=33). If that backtest is representative, you'd avoid a large ne Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com