LAB #2637 NEUTRAL: LEDGER BENCH: Apply filter: Session = NY_OPEN — improves win rate from 31.0% to 37.1% (+6.1pp, n=644 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = NY_OPEN — improves win rate from 31.0% to 37.1% (+6.1pp, n=644) SAME-WINDOW EFFECT: Applying the NY_OPEN filter to the current 10-trade window would have excluded all trades, as every entry timestamp falls between 10:10 and 11:35 CET (08:10–09:35 ET), which is outside the NY_OPEN session (typically 14:30–21:00 CET / 08:30–15:00 ET). This would have eliminated 6 wins, 4 losses, and the 1 rejected trade — net PnL change is ambiguous because the filter removes both winners and losers. The backtested +6.1pp win-rate improvement is not visible here; in fact, this window shows a 60% win rate without the filter, so the filter would have reduced realized win rate to 0% (no trades). The filter appears to be a session-selection bias that may simply avoid low-volatility hours, but this sample is too small and time-shifted to validate. OVER-TIME PROJECTION: Over 3–6 months, the NY_OPEN filter could pl Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com