LAB #2795 NEUTRAL: LEDGER BENCH: Apply filter: NZDUSD SHORT — improves win rate from 31.0% to 31.8% (+0.9pp, n=110) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: NZDUSD SHORT — improves win rate from 31.0% to 31.8% (+0.9pp, n=110) SAME-WINDOW EFFECT: Over the current 10-trade window, the NZDUSD SHORT filter would have had zero direct impact — none of the listed trades are NZDUSD. The +0.9pp win-rate improvement (n=110) is statistically marginal (p≈0.35), and the live window shows no NZDUSD exposure to validate or contradict it. Expected PnL delta in this window: $0. The filter would only matter if it indirectly altered signal routing or risk allocation, which it does not per the description. OVER-TIME PROJECTION: Over 3-6 months, a +0.9pp win-rate gain on a subset of trades (NZDUSD SHORT only) is unlikely to survive live slippage, spread costs, and regime shifts. The sample (n=110) is small; the effect could easily be noise. Risk: if the filter removes NZDUSD SHORT trades that are actually profitable in trending markets, you could lose more in missed gains t Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com