LAB #379 HARMFUL: LEDGER BENCH: Apply filter: USDCHF SHORT @ LONDON_OPEN with 6 conf — improves win rate from 32.4% to — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT @ LONDON_OPEN with 6 conf — improves win rate from 32.4% to 100.0% (+67.6pp, n=5) SAME-WINDOW EFFECT: Over the current live trade window, applying the USDCHF SHORT @ LONDON_OPEN with 6 conf filter would have affected only the USDCHF SHORT trade that was already a win (entry 0.81212, closed win). Since that trade already won, the filter would have confirmed it but not changed the outcome. No other trades in the window match the filter criteria (USDCHF SHORT at London open with 6 conf), so the win rate and PnL delta would be unchanged — the 100% win rate claim is based on only 5 historical samples, which is statistically meaningless. OVER-TIME PROJECTION: Over 3-6 months, this filter would likely degrade performance due to extreme overfitting on a tiny sample (n=5). The 67.6pp improvement is almost certainly noise — a 32.4% base win rate with 5 filtered trades could easily produce 5 wins

Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com