LAB #999 PROMISING: LEDGER BENCH: Apply filter: NZDUSD SHORT — improves win rate from 31.6% to 33.7% (+2.0pp, n=98) — E8 Intelligence Research

Abstract

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: NZDUSD SHORT — improves win rate from 31.6% to 33.7% (+2.0pp, n=98) SAME-WINDOW EFFECT: Over the current live trade window, applying the NZDUSD SHORT filter would have had no direct impact — none of the 10 listed trades involve NZDUSD. The filter only removes NZDUSD SHORT entries, so it would not alter any of the existing EURUSD, USDCAD, GBPUSD, XAUUSD, EURJPY, USDCHF, AUDUSD, or USDJPY trades. Win rate and PnL for this specific window remain unchanged. The +2.0pp improvement from backtests (n=98) suggests a modest but consistent edge when NZDUSD SHORT signals are excluded. OVER-TIME PROJECTION: Over 3-6 months, the filter is expected to lift overall win rate by roughly 2 percentage points, assuming the backtest sample (n=98) is representative and not overfitted. The primary risk is that the improvement is driven by a specific market regime (e.g., NZDUSD trending strongly against short entries) that Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com