LAB #1238 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT @ LONDON_OPEN with 5 conf — improves win rate from 31.5% to — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT @ LONDON_OPEN with 5 conf — improves win rate from 31.5% to 62.5% (+31.0pp, n=16) SAME-WINDOW EFFECT: Over the current trade window, the filter would have blocked the USDCHF SHORT via rizzy5m (entry=0.81212, CLOSED/WIN) because it was entered at 09:05, not London Open. No other USDCHF SHORT trades appear in the window. Thus, the filter would have removed a winning trade, reducing win count by 1 and likely decreasing PnL slightly — the 31.0pp win-rate improvement from the backtest does not replicate here. OVER-TIME PROJECTION: Over 3-6 months, the filter may improve win rate on USDCHF SHORT specifically, but the sample size (n=16) is critically small — a single outlier could drive the result. Risk includes overfitting to a narrow time/confidence window, potentially missing profitable setups outside London Open. The filter also reduces trade frequency, which could lower total PnL even if Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com