LAB #368 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF LONG @ LONDON_OPEN with 5 conf — improves win rate from 32.4% to — E8 Intelligence Research

Abstract

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF LONG @ LONDON_OPEN with 5 conf — improves win rate from 32.4% to 80.0% (+47.6pp, n=5) **SAME-WINDOW EFFECT:** Over the current trade window, no USDCHF LONG @ LONDON_OPEN trades with 5 conf appear in the live list — the only USDCHF trade is a SHORT via rizzy5m that closed as a win. Applying this filter would not have altered any open or closed positions in this window. The win-rate improvement claim (32.4% → 80.0%) is based on n=5, which is statistically fragile and likely reflects overfitting to a small sample rather than a robust edge. **OVER-TIME PROJECTION:** Over 3–6 months, this filter would likely degrade performance. The 5-conf threshold is extremely restrictive, producing very few signals — the 80% win rate on n=5 is almost certainly noise. In live running, the filter would miss the majority of USDCHF opportunities, and the few trades taken would regress toward the base win rate ( Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com