LAB #3008 NEUTRAL: LEDGER BENCH: Apply filter: Session = LONDON_OPEN — improves win rate from 31.3% to 31.7% (+0.5pp, n — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = LONDON_OPEN — improves win rate from 31.3% to 31.7% (+0.5pp, n=252) SAME-WINDOW EFFECT: Applying the LONDON_OPEN filter to the current 10-trade window would have excluded the two XAUUSD trades (entries at 10:10 and 11:35 on Aug 6/4) and the AUDUSD/USDCAD/USDJPY trades at 11:23/11:20/11:15 — all outside a strict London open (07:00–09:00 UTC). Of the excluded trades, 3 were wins (XAUUSD LONG, AUDUSD LONG, USDCAD SHORT) and 2 were losses (XAUUSD SHORT, USDJPY SHORT), netting +1 win. The remaining 5 trades (all GBPUSD/USDCHF) would have been 3 wins, 1 loss, 1 rejected — a win rate of 75% vs. the current 60% (6W/4L), a +15pp improvement on this tiny sample. PnL delta is positive but fragile: removing 2 wins and 2 losses shifts the balance, yet the filter's claimed +0.5pp is statistically indistinguishable from noise at n=252. OVER-TIME PROJECTION: Over 3–6 months, a 0.5pp win-rate gain on ~500– Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com