LAB #4771 NEUTRAL: LEDGER BENCH: Apply filter: NZDUSD LONG — improves win rate from 31.8% to 54.5% (+22.7pp, n=121) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: NZDUSD LONG — improves win rate from 31.8% to 54.5% (+22.7pp, n=121) SAME-WINDOW EFFECT: The filter only gates NZDUSD LONG entries, and the current live window contains exactly one NZDUSD trade — a SHORT (rizzy5m, 2026-09-09) that was already REJECTED. So zero live trades change: no entry suppressed, no loss avoided, no win captured. The +22.7pp headline is therefore untested by this window and cannot be credited or debited against it. Net delta on the current book: 0 trades, 0 PnL, 0 win-rate change. OVER-TIME PROJECTION: If the 54.5% vs 31.8% split is real and out-of-sample, this is a meaningful edge on a single pair-direction — but n=121 with a 22.7pp jump is exactly the profile of a filter fitted to a handful of regime-specific winners, and NZDUSD LONG is a carry/risk-sentiment expression that flips hard with rate differentials and USD liquidity. Over 3-6 months expect the effect to decay toward Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com