LAB #2306 NEUTRAL: LEDGER BENCH: Apply filter: NZDUSD SHORT — improves win rate from 31.5% to 34.3% (+2.8pp, n=102) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: NZDUSD SHORT — improves win rate from 31.5% to 34.3% (+2.8pp, n=102) SAME-WINDOW EFFECT: Over the current 10-trade window, the NZDUSD SHORT filter would have had zero direct impact — no NZDUSD trades are present in the live list. The +2.8pp win-rate improvement is derived from a separate 102-trade backtest sample, not from this window. If applied, it would not alter any of the 10 live outcomes (3 wins, 4 losses, 3 open), so PnL delta here is exactly 0. The filter is orthogonal to current exposure, meaning no immediate benefit or harm in this specific window. OVER-TIME PROJECTION: Over 3-6 months, a +2.8pp win-rate gain on NZDUSD shorts could translate to meaningful edge if the sample is stable and not overfit. However, n=102 is small; the confidence interval is roughly ±9.5pp at 95% (using normal approximation), so the true effect could be negative. Risk: the filter may be curve-fit to a specific re Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com