LAB #4176 NEUTRAL: LEDGER BENCH: Apply filter: Session = OFF_SESSION — improves win rate from 32.6% to 42.5% (+9.9pp, n — E8 Intelligence Research
Year: 2026
Type: preprint
Abstract: IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Session = OFF_SESSION — improves win rate from 32.6% to 42.5% (+9.9pp, n=127) SAME-WINDOW EFFECT: Applying the OFF_SESSION filter would have excluded the three wkjudas trades (GBPUSD LONG, USDJPY SHORT, NZDUSD SHORT) and the rizzy5m AUDUSD SHORT from 08-27, all of which were losses or open/rejected. That removes 4 of 10 trades, eliminating 3 confirmed losses and 1 open/rejected, leaving only the two rizzy5m wins and the rizzy7m loss. Expected win rate in this window would rise from 3/10 (30%) to 2/3 (66.7%), but PnL delta is ambiguous — you lose the rejected/open trade's potential and the sample shrinks to near-zero statistical power. OVER-TIME PROJECTION: Over 3-6 months, the +9.9pp improvement on n=127 is real but fragile — it likely reflects a regime where OFF_SESSION hours (Asian/early London) had lower volatility and cleaner trends, not a structural edge. Risk: the filter may overfit to a speci 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: W7222896138
Cites:
Cited by:
Related to: