LAB #4933 NEUTRAL: LEDGER BENCH: Apply filter: NZDUSD LONG @ NY_OPEN with 6 conf — improves win rate from 31.7% to 82.8 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: NZDUSD LONG @ NY_OPEN with 6 conf — improves win rate from 31.7% to 82.8% (+51.0pp, n=29) SAME-WINDOW EFFECT: This filter would not have touched a single trade in the live window above — every logged position is either a SHORT (EURUSD, XAUUSD, AUDUSD, NZDUSD, GBPUSD, EURJPY, USDCAD) or a USDCHF LONG, and none are NZDUSD LONGs at NY_OPEN. The window's realized results (3 closed losses, 2 closed wins, 5 rejected/open) would be unchanged, so the +51.0pp claim is entirely untested against the trades that actually ran. Note also the filter's direction (LONG) is the opposite of the NZDUSD SHORT that was rejected on 09-09 — the model is currently leaning short NZD, which makes a long-only NY_OPEN carve-out a directional bet, not a neutral filter. OVER-TIME PROJECTION: n=29 is the core problem. A 31.7% → 82.8% jump on 29 samples means roughly 9 wins becoming 24 wins — that is a handful of trades flipping, w Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com