LAB #997 NEUTRAL: LEDGER BENCH: Apply filter: EURUSD LONG — improves win rate from 31.6% to 36.4% (+4.7pp, n=44) — E8 Intelligence Research

Abstract

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: EURUSD LONG — improves win rate from 31.6% to 36.4% (+4.7pp, n=44) SAME-WINDOW EFFECT: Over the current trade window, applying a EURUSD LONG filter would have blocked the EURUSD SHORT trade that closed as a loss, directly improving win rate by removing one losing trade from the sample. However, it would not have affected any other trades since no EURUSD LONG entries were present in the window. The net PnL delta would be positive by the amount of that single loss, but the sample size is too small to draw meaningful conclusions about broader performance. OVER-TIME PROJECTION: Over 3-6 months, a EURUSD LONG filter could modestly improve win rate if the strategy systematically underperforms on EURUSD shorts relative to longs. However, the reported improvement of +4.7pp from n=44 is statistically weak and may be due to random variation or overfitting to a specific market regime. Risk includes missing pro Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com