LAB #1861 NEUTRAL: LEDGER BENCH: Apply filter: ETHUSD SHORT — improves win rate from 32.0% to 50.8% (+18.9pp, n=59) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: ETHUSD SHORT — improves win rate from 32.0% to 50.8% (+18.9pp, n=59) SAME-WINDOW EFFECT: Applying the ETHUSD SHORT filter would have zero effect on the current live window, as none of the 10 listed trades involve ETHUSD. The filter is symbol-direction-specific, so it cannot alter outcomes for GBPUSD, XAUUSD, EURJPY, AUDUSD, or USDJPY. Therefore, the claimed +18.9pp win-rate improvement is untestable against this window — it neither helps nor hurts current open positions. PnL delta: 0. OVER-TIME PROJECTION: Over 3-6 months, the filter would only affect a subset of ETHUSD SHORT entries (n=59 in backtest). The jump from 32% to 50.8% is statistically fragile — a 95% confidence interval around 50.8% with n=59 spans roughly ±12.7pp, meaning true win rate could be as low as 38%. The main risk is overfitting to a specific regime (e.g., ETHUSD trending down in that backtest window); if the market flips to ra Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com