LAB #2396 NEUTRAL: LEDGER BENCH: Apply filter: NZDUSD SHORT @ NY with 5 conf — improves win rate from 31.1% to 60.0% (+ — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: NZDUSD SHORT @ NY with 5 conf — improves win rate from 31.1% to 60.0% (+28.9pp, n=15) SAME-WINDOW EFFECT: Over the current 10-trade window, the filter would have blocked only NZDUSD trades — none appear in the live list. Therefore, zero trades are affected, and win rate/PnL delta is exactly 0.0pp. The claimed +28.9pp improvement is untestable here because the window contains no NZDUSD SHORT entries. This is a null result for the current sample, not evidence for or against the filter. OVER-TIME PROJECTION: Over 3–6 months, a filter that only applies to one pair/session/confidence combo will likely see regression toward the mean, especially given n=15. The base win rate of 31.1% is low, but 60% on 15 trades has a wide confidence interval (roughly 35–80%). Risk: the filter may be overfit to a specific NY-session volatility regime; if that regime shifts, the edge could invert. Also, filtering out NZDUSD Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com