LAB #2048 NEUTRAL: LEDGER BENCH: Apply filter: Session = NY_OPEN — improves win rate from 32.0% to 38.3% (+6.3pp, n=622 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = NY_OPEN — improves win rate from 32.0% to 38.3% (+6.3pp, n=622) SAME-WINDOW EFFECT: Applying the NY_OPEN filter would have excluded all 10 listed trades, since every entry timestamp falls outside the NY open session (all are between 09:55 and 20:00 UTC+2, with most clustered in the European morning). The live window shows 4 wins, 4 losses, 1 open, 1 expired — a 50% win rate on closed trades, which is already above your backtested 38.3% for NY_OPEN. Therefore, this filter would have removed all trades and produced zero PnL — a net negative versus the actual +2 wins over losses. The backtest improvement is not reflected in this sample because the filter would have eliminated the entire sample, not improved it. OVER-TIME PROJECTION: Over 3-6 months, restricting to NY_OPEN will reduce trade frequency dramatically (likely 60-80% fewer entries), which may concentrate risk into a narrower time wi Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com