LAB #4955 NEUTRAL: LEDGER BENCH: Apply filter: Session = NY_OPEN — improves win rate from 31.7% to 38.6% (+6.9pp, n=811 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = NY_OPEN — improves win rate from 31.7% to 38.6% (+6.9pp, n=811) SAME-WINDOW EFFECT: The NY_OPEN filter would have blocked most of the live window's trades, because nearly every entry timestamp here is ~10:25–11:45 CET — i.e. London morning / pre-NY, not NY open. That means the three closed losses (EURUSD, XAUUSD, AUDUSD) and the USDCHF win would likely have been filtered out, leaving only the two USDCAD trades (one win, one rejected) and the later NY-session entries. Net effect on this tiny sample: fewer trades, loss avoidance, but also removal of the only clean win — so the apparent win-rate lift is mostly a sample-size artifact, not demonstrated edge. The +6.9pp figure cannot be validated from this window because the filter is not actually selecting the trades shown. OVER-TIME PROJECTION: If NY_OPEN genuinely carries a 38.6% win rate vs 31.7% baseline at n=811, that is a meaningful condi Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com