LAB #2332 NEUTRAL: LEDGER BENCH: Apply filter: Session = LONDON_OPEN — improves win rate from 31.6% to 32.3% (+0.7pp, n — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = LONDON_OPEN — improves win rate from 31.6% to 32.3% (+0.7pp, n=235) SAME-WINDOW EFFECT: Applying the LONDON_OPEN filter would have excluded all 10 live trades shown, since every entry timestamp falls between 09:55 and 18:00+02:00 — none are strictly within a defined London open session (typically 08:00–09:00 UTC, i.e., 10:00–11:00 CEST). The only borderline candidate is the XAUUSD LONG at 10:10:00+02:00, which sits just 10 minutes past a strict London-open window; if included, that trade was a WIN, so the filter would have removed 9 trades (4 wins, 5 losses) and possibly kept 1 win. Net effect on this tiny sample: win rate would jump from 40% (4/10) to either 100% (1/1) or 0% (0/0) — statistically meaningless, and the +0.7pp backtest gain is within noise for n=235. OVER-TIME PROJECTION: Over 3–6 months, this filter would reduce trade frequency by roughly 60–70% (London open is only ~1–2 ho Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com