LAB #977 PROMISING: LEDGER BENCH: Apply filter: USDCHF SHORT @ ASIAN with 5 conf — improves win rate from 31.6% to 63.2% — E8 Intelligence Research

Abstract

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT @ ASIAN with 5 conf — improves win rate from 31.6% to 63.2% (+31.5pp, n=19) SAME-WINDOW EFFECT: Over the current live trade window, this filter would have blocked the USDCHF SHORT via rizzy5m (entry=0.81212, CLOSED/WIN) — a winning trade that contributed positively to the ledger. Removing that win from the sample would reduce the observed win rate in this window, not improve it, since the filter targets USDCHF SHORT @ ASIAN with 5 conf and that trade likely met the criteria. The net PnL delta would be negative for this specific window, as you lose a confirmed winner. However, the backtest claim of +31.5pp win rate improvement (n=19) suggests the filter's benefit may appear over a larger, more diverse sample than this 10-trade snapshot. OVER-TIME PROJECTION: Over 3-6 months, applying this filter could meaningfully reduce losses from low-confidence USDCHF SHORT entries during Asian hours, Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com