LAB #4147 NEUTRAL: LEDGER BENCH: Apply filter: NZDUSD SHORT — improves win rate from 32.5% to 34.1% (+1.5pp, n=132) — E8 Intelligence Research

Abstract

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: NZDUSD SHORT — improves win rate from 32.5% to 34.1% (+1.5pp, n=132) SAME-WINDOW EFFECT: Applying the NZDUSD SHORT filter would have blocked the NZDUSD SHORT via rizzy5m (entry 0.58252, CLOSED/WIN) and the NZDUSD SHORT via wkjudas (entry 0.59214, CLOSED/open). That removes one confirmed win and one open/possibly profitable trade from the window. The remaining NZDUSD SHORT via rizzy5m (entry 0.59416, CLOSED/LOSS) would also be blocked, but it was already a loss. Net effect: you lose a win and an open positive, while avoiding one loss — likely a negative PnL delta in this specific window, despite the backtest's marginal win-rate gain. OVER-TIME PROJECTION: Over 3–6 months, a +1.5pp win-rate gain on n=132 is statistically weak (standard error ~4.3pp), so the true effect could easily be zero or negative. The filter appears to be curve-fit to a small sample, especially since it targets a single pair-dire Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com