LAB #1869 NEUTRAL: LEDGER BENCH: Apply filter: Session = LONDON_OPEN — improves win rate from 32.0% to 32.9% (+0.9pp, 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 32.0% to 32.9% (+0.9pp, n=231) SAME-WINDOW EFFECT: Applying the LONDON_OPEN filter to the live window would have excluded the EURJPY LONG (18:00) and GBPUSD LONG (20:00) trades on 2026-07-29, both of which were winners. That removes two wins from the sample, dropping the live win rate from 5/9 (55.6%) to 3/7 (42.9%) — a net negative in this specific window. The filter would also have excluded the USDJPY SHORT (02:01) which was rejected anyway, so no real impact there. The remaining trades (rizzy5m entries around 09:55–11:45) are mostly within London hours, so the filter would not have saved any losses in this window — it would have only removed winners. Net PnL delta in this window: negative, roughly −2 wins worth of profit. OVER-TIME PROJECTION: Over 3–6 months, a +0.9pp win-rate improvement on n=231 is statistically fragile — the standard error on a 3 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: W7208828612
Cites:
Cited by:
Related to: