LAB #2266 NEUTRAL: LEDGER BENCH: Apply filter: NZDUSD SHORT — improves win rate from 31.6% to 34.3% (+2.7pp, n=102) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: NZDUSD SHORT — improves win rate from 31.6% to 34.3% (+2.7pp, n=102) SAME-WINDOW EFFECT: Applying the NZDUSD SHORT filter would have excluded zero trades from the current live window, as none of the ten listed positions involve NZDUSD. Therefore, the immediate PnL and win-rate impact on this specific sample is nil — the +2.7pp improvement is derived from a separate backtest population (n=102) that does not overlap with the live trades shown. The filter's effect here is purely hypothetical, and no trade in the current window would have been blocked or added, so the live outcome remains unchanged. OVER-TIME PROJECTION: Over 3-6 months, the filter could plausibly lift overall win rate by ~2-3pp if the NZDUSD SHORT edge persists, but the sample size (n=102) is marginal and likely includes regime-specific behavior (e.g., carry unwind, USD strength). The risk is overfitting to a narrow pair-direction slic Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com