LAB #2271 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT — improves win rate from 31.6% to 59.4% (+27.8pp, n=170) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT — improves win rate from 31.6% to 59.4% (+27.8pp, n=170) SAME-WINDOW EFFECT: Over the current live window, applying a USDCHF SHORT-only filter would have excluded zero of the 10 listed trades (none are USDCHF), so no direct PnL change here. However, the filter's claimed +27.8pp win-rate improvement (n=170) is suspiciously large for a single-pair directional filter — likely overfit to a specific regime (e.g., USD strength or CHF weakness). If applied globally, it would have blocked any USDCHF LONGs that may have occurred in the broader unseen sample, but within this window it is inert. Expected delta: 0 trades affected, 0 PnL change. OVER-TIME PROJECTION: Over 3–6 months, a USDCHF SHORT-only filter will likely degrade as USD/CHF mean-reverts or CHF strengthens (e.g., SNB intervention). The backtest's n=170 is small, and the +27.8pp jump suggests curve-fitting to a recent trend; live, you Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com