LAB #4006 NEUTRAL: LEDGER BENCH: Apply filter: Session = LONDON — improves win rate from 32.5% to 38.1% (+5.6pp, n=21) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = LONDON — improves win rate from 32.5% to 38.1% (+5.6pp, n=21) SAME-WINDOW EFFECT: Applying the LONDON session filter to the current live window would have excluded the 02:43 NZDUSD SHORT (wkjudas) and the 03:57 USDJPY SHORT (wkjudas), both outside London hours (assuming London = 07:00–16:00 UTC+2). Of the remaining 8 trades, the current window shows 2 wins, 3 losses, 2 open, 1 rejected — a raw win rate of 40% (2/5 closed). Removing the two non-London trades (both losses) would shift closed outcomes to 2 wins, 1 loss (66.7%), a +26.7pp improvement on this tiny sample. PnL delta is positive but negligible in absolute terms given n=3 closed trades; the rejected AUDUSD would remain unaffected. OVER-TIME PROJECTION: Over 3–6 months, the +5.6pp backtest gain (n=21) suggests a real but fragile edge — likely driven by tighter spreads and higher liquidity during London, which reduces slippage and i Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com