LAB #2280 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF LONG — improves win rate from 31.6% to 34.8% (+3.2pp, n=92) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF LONG — improves win rate from 31.6% to 34.8% (+3.2pp, n=92) SAME-WINDOW EFFECT: Applying a USDCHF LONG-only filter would have excluded none of the 10 live trades above (no USDCHF trades present), so the immediate window shows zero direct impact. However, the filter would have blocked any hypothetical USDCHF LONG entries that might have occurred in the same period — none did. The claimed +3.2pp win-rate improvement (31.6%→34.8%, n=92) is statistically marginal (p≈0.15, not significant at 95% CI). PnL delta in this window: effectively nil, but the filter adds a constraint that could reduce trade frequency without proven benefit. OVER-TIME PROJECTION: Over 3–6 months, a USDCHF LONG-only filter would likely reduce total trade count by ~5–8% (USDCHF is not a dominant pair in your current mix). The +3.2pp win-rate gain, if real, would translate to roughly +1–2% net PnL improvement, but the small sa Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com