LAB #4167 NEUTRAL: LEDGER BENCH: Apply filter: NZDUSD SHORT — improves win rate from 32.6% to 34.1% (+1.5pp, n=132) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: NZDUSD SHORT — improves win rate from 32.6% to 34.1% (+1.5pp, n=132) SAME-WINDOW EFFECT: Applying the NZDUSD SHORT filter would have blocked the two losing NZDUSD SHORT trades (rizzy5m on 2026-08-27 and wkjudas on 2026-09-01) while allowing the winning rizzy5m trade on 2026-09-02. That removes 2 losses from the 10-trade window, shifting the record from 3W/6L/1open to 3W/4L/1open — a raw win-rate improvement from ~33% to ~43% on this tiny sample. However, the filter would also have blocked the open NZDUSD SHORT via wkjudas (entry 0.59214), which is currently marked [CLOSED/open] — if that later closes as a win, the benefit shrinks; if it closes as a loss, the filter looks even better. Net PnL delta is positive but driven by only 2–3 trades, so it is statistically fragile. OVER-TIME PROJECTION: Over 3–6 months, the claimed +1.5pp win-rate gain (n=132) is marginal and likely within noise for a single-p Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com