LAB #2217 NEUTRAL: LEDGER BENCH: Apply filter: Session = NY_OPEN — improves win rate from 31.9% to 38.0% (+6.2pp, n=626 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = NY_OPEN — improves win rate from 31.9% to 38.0% (+6.2pp, n=626) SAME-WINDOW EFFECT: Applying the NY_OPEN filter would have excluded all 10 listed trades, as every entry timestamp falls outside the NY open session (all are between 09:55 and 20:00 UTC+2, with no 14:30–17:00 UTC+2 entries). This means the filter would have eliminated 4 wins and 4 losses (plus 1 open, 1 pending) — net effect on this window is zero PnL change, but it would have removed all activity, reducing exposure and variance. The backtested +6.2pp win-rate gain does not manifest here because no trades would have been taken; the filter acts as a total gate, not a selective enhancer, in this sample. OVER-TIME PROJECTION: Over 3–6 months, the NY_OPEN filter could plausibly lift win rate if the edge is real, but the sample (n=626) is modest and the +6.2pp could be regime-dependent (e.g., higher volatility during NY open in tre Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com