LAB #2333 NEUTRAL: LEDGER BENCH: Apply filter: Session = NY_OPEN — improves win rate from 31.6% to 38.0% (+6.4pp, n=629 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = NY_OPEN — improves win rate from 31.6% to 38.0% (+6.4pp, n=629) SAME-WINDOW EFFECT: Applying the NY_OPEN session filter to the 10 live trades above would have excluded all 10, since every entry timestamp falls outside the NY open (all are 09:55–18:00+02:00, which is 03:55–12:00 ET — none in the 09:30–10:30 ET NY open window). This means the filter would have eliminated 4 wins and 6 losses, converting the window to zero trades. Net PnL delta is roughly zero (no trades taken), but variance drops to nil — the apparent +6.4pp win-rate gain in backtest does not translate to this sample because the filter is too restrictive for the current live execution times. OVER-TIME PROJECTION: Over 3–6 months, this filter would drastically cut trade frequency (likely 60–80% reduction) while concentrating only on a narrow 1-hour window. The backtest gain of +6.4pp on n=629 is modest and may be regime-depend Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com