LAB #1904 NEUTRAL: LEDGER BENCH: Apply filter: NZDUSD LONG @ NY_OPEN with 6 conf — improves win rate from 32.0% to 91.7 — 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 32.0% to 91.7% (+59.7pp, n=12) SAME-WINDOW EFFECT: Over the current live window, this filter would have had **zero effect** — none of the 10 listed trades are NZDUSD, and none were opened at NY_OPEN with a 6-conf trigger. The filter is pair- and time-specific, so it would not have altered any of the GBPUSD, XAUUSD, EURJPY, AUDUSD, or EURUSD outcomes. The claimed +59.7pp win-rate improvement is therefore **untestable against this window** — it neither helps nor hurts the trades shown. Expected PnL delta: $0. OVER-TIME PROJECTION: Over 3–6 months, this filter would only matter if NZDUSD LONG @ NY_OPEN with 6 conf is a recurring signal. With n=12, the 91.7% win rate is statistically fragile — a single loss flips it to 83.3%, and two losses to 75%. The filter likely overfits to a narrow regime (likely a quiet Asian-session-to-NY transition patte Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com