LAB #2362 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT @ NY_OPEN with 5 conf — improves win rate from 31.2% to 64. — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT @ NY_OPEN with 5 conf — improves win rate from 31.2% to 64.2% (+33.0pp, n=67) SAME-WINDOW EFFECT: Over the current live window, this filter would have blocked the three USDCHF SHORT trades that are not present in the list — meaning zero direct impact on the 10 trades shown, since none are USDCHF. However, the filter's logic (SHORT only at NY_OPEN with 5 conf) would have also excluded any hypothetical USDCHF shorts that might have been taken but are absent from the visible list. The win-rate improvement cited (+33pp) is based on n=67, which is small and likely overfit to a specific regime; applying it to the current window would change nothing observable, so the PnL delta is ~0. The real risk is that the filter is curve-fit to a narrow time slice, and its apparent edge may vanish out-of-sample. OVER-TIME PROJECTION: Over 3–6 months, this filter would reduce trade frequency on USDCHF SHOR Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com