LAB #2606 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF LONG — improves win rate from 31.0% to 34.8% (+3.7pp, n=92) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF LONG — improves win rate from 31.0% to 34.8% (+3.7pp, n=92) SAME-WINDOW EFFECT: Over the current live window, the USDCHF SHORT at 0.81122 (rizzy5m) would have been blocked by a LONG-only filter — that trade is currently open/rejected, so no direct PnL change yet. The other 9 trades are unaffected (GBPUSD, XAUUSD, AUDUSD, USDCAD, USDJPY). The +3.7pp win-rate gain is derived from a backtest sample of n=92, but this window contains only 1 USDCHF signal, so the live delta here is negligible — likely <0.5% win-rate shift and near-zero PnL impact. OVER-TIME PROJECTION: Over 3–6 months, a LONG-only USDCHF filter would remove all short signals on that pair. If the backtest is accurate, you gain ~3.7pp win rate but sacrifice short-side opportunities — which may include high-RR trades. The risk is regime dependence: USDCHF has trended down in this period; a LONG filter could miss the dominant short tre Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com