LAB #4624 NEUTRAL: LEDGER BENCH: Apply filter: Session = OFF_SESSION — improves win rate from 32.2% to 42.2% (+10.0pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = OFF_SESSION — improves win rate from 32.2% to 42.2% (+10.0pp, n=128) SAME-WINDOW EFFECT: Applying the OFF_SESSION filter would have blocked the 10:41 USDCHF LONG, the 11:35 EURJPY SHORT, and the 09:56 AUDUSD LONG — all currently REJECTED/open, meaning no live PnL change from those. Among the closed trades, none fall outside the filter's definition of OFF_SESSION (all entries are between 09:15 and 15:08, which appear to be within active sessions), so the win rate in this window would remain 4 wins / 6 closed = 66.7%, unchanged. The +10pp backtest gain is not observable here because the live window is too small and lacks qualifying off-session entries. Expected PnL delta: zero for this specific set. OVER-TIME PROJECTION: Over 3–6 months, if the backtest edge is real, you would see fewer trades overall (roughly 20–30% reduction if OFF_SESSION is defined as non-London/NY overlap), with a highe Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com