LAB #2093 NEUTRAL: LEDGER BENCH: Apply filter: NZDUSD SHORT — improves win rate from 32.0% to 33.7% (+1.6pp, n=101) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: NZDUSD SHORT — improves win rate from 32.0% to 33.7% (+1.6pp, n=101) SAME-WINDOW EFFECT: Applying a blanket NZDUSD SHORT filter would have zero effect on the current live window — none of the 10 listed trades involve NZDUSD. The backtest improvement (+1.6pp win rate, n=101) is statistically marginal (p≈0.15, not significant) and likely driven by a specific regime (e.g., NZD weakness vs USD strength) rather than a durable edge. If applied live, it would only suppress future NZDUSD SHORT entries, potentially avoiding a few losses but also missing any wins — net PnL delta in this window is exactly 0. OVER-TIME PROJECTION: Over 3–6 months, this filter would reduce trade frequency on NZDUSD SHORTs by ~100%, which could improve win rate slightly if the pair's short-side behavior is persistently adverse. However, the sample (n=101) is too small to distinguish signal from noise; a 1.6pp win-rate shift is wi Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com