LAB #359 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF LONG @ NY_OPEN with 6 conf — improves win rate from 32.4% to 71.4 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF LONG @ NY_OPEN with 6 conf — improves win rate from 32.4% to 71.4% (+39.1pp, n=14) SAME-WINDOW EFFECT: Over the current trade window, the USDCHF LONG @ NY_OPEN with 6 conf filter would have directly conflicted with the live USDCHF SHORT via rizzy5m that closed as a win. If this filter had been active, it would have blocked that short entry, preventing a +win but also avoiding any potential long entry that might have occurred at NY_OPEN. Given the small sample (n=14), the +39.1pp win rate improvement is statistically fragile, and in this specific window, the net effect would likely be neutral to slightly negative, as the blocked short win is not offset by a confirmed long win. OVER-TIME PROJECTION: Over 3-6 months, this filter could produce a meaningful win-rate improvement if the 71.4% holds, but the tiny sample (n=14) means high variance risk. The filter is highly specific (USDCHF, LONG, NY_ Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com