LAB #2055 NEUTRAL: LEDGER BENCH: Apply filter: Session = OFF_SESSION — improves win rate from 31.9% to 44.9% (+12.9pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = OFF_SESSION — improves win rate from 31.9% to 44.9% (+12.9pp, n=98) SAME-WINDOW EFFECT: Applying the OFF_SESSION filter to the current live window would have removed the three XAUUSD SHORT trades (all losses) and the EURJPY SHORT (win), plus the AUDUSD LONG (win) and USDCAD SHORT (win) — depending on exact session definitions. If the filter excludes all trades outside the defined OFF_SESSION hours, you'd drop 2 wins and 3 losses from the 10 shown, shifting the raw win rate from ~50% (5/10) to ~60% (3/5) on the remaining trades. The PnL delta is positive but small in absolute terms, as the removed losses (XAUUSD shorts) likely outweigh the removed wins in magnitude. The open USDJPY SHORT is unaffected if it falls inside the session. OVER-TIME PROJECTION: Over 3-6 months, a +12.9pp win-rate improvement on n=98 is statistically weak (95% CI roughly ±9-10pp), so the true effect could be near z Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com