LAB #4622 NEUTRAL: LEDGER BENCH: Apply filter: Session = LONDON_OPEN — improves win rate from 32.2% to 35.9% (+3.7pp, n — E8 Intelligence Research
Year: 2026
Type: preprint
Abstract: IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = LONDON_OPEN — improves win rate from 32.2% to 35.9% (+3.7pp, n=368) SAME-WINDOW EFFECT: Applying the LONDON_OPEN filter (assuming 08:00–12:00 UTC+2) would have excluded all three REJECTED/open trades (USDCHF 10:41, EURJPY 11:35, AUDUSD 09:56) — but those are already flagged as rejected by the engine, so the filter adds no new exclusions there. Among the closed trades, only GBPUSD SHORT (11:50) and AUDUSD SHORT (10:15) fall inside the window; both are wins/losses already captured. The net effect on this small sample is zero — the +3.7pp backtest gain does not manifest here because the live window is dominated by non-London entries and the filter would not have altered any closed outcome. OVER-TIME PROJECTION: Over 3–6 months, the filter would reduce trade frequency by roughly 60–70% (only ~4–5 hours of the 24-hour day), which could concentrate risk into a narrow volatility burst. The backte Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
Author: Caldin, Andrew Stewart
Language: English
Subfield: Finance
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7223468291
Cites:
Cited by:
Related to: