LAB #2723 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF LONG @ LONDON_OPEN with 5 conf — improves win rate from 30.9% to — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF LONG @ LONDON_OPEN with 5 conf — improves win rate from 30.9% to 80.0% (+49.1pp, n=5) SAME-WINDOW EFFECT: Over the current live window, this filter would have blocked the two USDCHF trades (the rejected SHORT at 0.81122 and any hypothetical LONGs). Since the only USDCHF signal was a SHORT (not a LONG), the filter would have had zero effect on the existing 10 trades — no win-rate change, no PnL delta. The 80% win rate claim is based on n=5, which is statistically meaningless; the observed 30.9% baseline likely includes all pairs/sessions, so this is an apples-to-oranges comparison. OVER-TIME PROJECTION: Over 3–6 months, this filter would likely reduce trade frequency (USDCHF LONGs at London open are rare) while marginally improving win rate if the edge is real — but with n=5, the true win rate could easily be 40–60% (95% CI roughly ±40pp). The main risk is overfitting to a tiny sample: London- Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com