LAB #2673 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT — improves win rate from 31.1% to 59.1% (+28.0pp, n=171) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT — improves win rate from 31.1% to 59.1% (+28.0pp, n=171) SAME-WINDOW EFFECT: Over the current live window, the filter would have blocked the USDCHF SHORT (currently REJECTED/open) and, if applied historically, would also have removed the USDJPY SHORT (a loss) — but it would not have touched the two GBPUSD SHORT wins or the XAUUSD LONG win. Net effect on the 10 trades shown: you'd remove 1 loss (USDJPY) and 1 open/unknown (USDCHF), leaving 5 wins and 3 losses → win rate improves from 5/9 (55.6%) to 5/8 (62.5%) on closed trades, but the sample is tiny and the USDCHF trade was already rejected, so the live delta is near zero. The claimed +28pp comes from a different, larger backtest window (n=171) — that is not visible in this 10-trade slice. OVER-TIME PROJECTION: Over 3–6 months, if the 31.1% → 59.1% win-rate improvement holds out-of-sample, this filter would meaningfully reduce drawdown Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com