LAB #2016 NEUTRAL: LEDGER BENCH: Apply filter: NZDUSD LONG — improves win rate from 31.9% to 34.9% (+3.0pp, n=63) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: NZDUSD LONG — improves win rate from 31.9% to 34.9% (+3.0pp, n=63) SAME-WINDOW EFFECT: Over the current 10-trade window, the NZDUSD LONG filter would have had zero direct impact — no NZDUSD trades are present in the live list. The claimed +3.0pp win-rate improvement (31.9%→34.9%) is based on n=63 backtest trades, but the live window contains only 10 trades across 6 different pairs, so the filter would not have altered any of these outcomes. The PnL delta over this specific window is therefore exactly $0. The only indirect effect would be if the filter changed signal generation logic globally (e.g., resource allocation), but as stated it is a pair-direction filter, so no trade here is affected. OVER-TIME PROJECTION: Over 3–6 months, a +3.0pp win-rate gain on NZDUSD LONG could translate to meaningful edge if the sample is stable and not overfit. However, n=63 is small — the 95% confidence interval aro Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com