LAB #307 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF LONG @ NY_OPEN with 6 conf — improves win rate from 32.3% to 71.4 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF LONG @ NY_OPEN with 6 conf — improves win rate from 32.3% to 71.4% (+39.1pp, n=14) **SAME-WINDOW EFFECT:** Over the current trade window, the USDCHF SHORT via rizzy5m (CLOSED/WIN) would not have been affected, as the filter targets LONG entries at NY_OPEN with 6 conf. No USDCHF LONG trades appear in the live window, so the filter would have had zero impact on PnL or win rate. The win rate improvement claim (32.3% → 71.4%) is based on a tiny sample (n=14) and cannot be validated against this window. **OVER-TIME PROJECTION:** Over 3-6 months, the filter may show a genuine edge if the 6-conf condition reliably selects high-probability USDCHL LONG entries at NY_OPEN. However, the sample size (n=14) is dangerously small — a single outlier could skew results. Risk includes overfitting to a specific market regime (e.g., trending USD strength) that may not persist. Expect high variance and potent Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com