LAB #3999 NEUTRAL: LEDGER BENCH: Apply filter: ETHUSD SHORT — improves win rate from 32.5% to 50.0% (+17.5pp, n=74) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: ETHUSD SHORT — improves win rate from 32.5% to 50.0% (+17.5pp, n=74) SAME-WINDOW EFFECT: Applying the ETHUSD SHORT filter would have had zero impact on the current live window, as none of the 10 listed trades involve ETHUSD. The filter is symbol-specific, so it would not alter any NZDUSD, AUDUSD, XAUUSD, GBPUSD, EURJPY, EURUSD, USDJPY, or USDCHF outcomes. Therefore, the win-rate delta in this window is exactly 0.0pp, and PnL remains unchanged. The claimed +17.5pp improvement is entirely derived from a separate backtest sample (n=74) and cannot be validated against this live set. OVER-TIME PROJECTION: Over 3-6 months, the filter could genuinely improve ETHUSD short performance if the 50% win rate holds — but the sample is tiny (n=74) and the improvement is suspiciously large (+17.5pp), suggesting possible overfitting to a specific regime (e.g., a trending down market). The risk is that the filter may Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com