LAB #2663 NEUTRAL: LEDGER BENCH: Apply filter: NZDUSD LONG — improves win rate from 31.1% to 36.8% (+5.7pp, n=68) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: NZDUSD LONG — improves win rate from 31.1% to 36.8% (+5.7pp, n=68) SAME-WINDOW EFFECT: Applying a NZDUSD LONG-only filter would have had zero effect on the current live window — none of the 10 trades listed are NZDUSD, and no NZDUSD trades appear in the GTX setup results. The claimed +5.7pp win-rate improvement (n=68) is derived from a historical backtest subset, not from this window, so the live PnL delta here is exactly 0.00. The filter would not have blocked or added any trade, leaving all 10 outcomes unchanged. This is a null-effect test for the current window — it neither helps nor hurts. OVER-TIME PROJECTION: Over 3–6 months, a single-pair, single-direction filter is likely to be curve-fit to a specific regime (e.g., NZD strength during a carry unwind or commodity rally). The +5.7pp improvement on n=68 is statistically fragile — the 95% confidence interval around that delta spans roughly ±11pp Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com