LAB #4037 PROMISING: LEDGER BENCH: Apply filter: Session = OFF_SESSION — improves win rate from 32.5% to 42.9% (+10.3pp, — 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 32.5% to 42.9% (+10.3pp, n=126) SAME-WINDOW EFFECT: Applying the OFF_SESSION filter would have blocked the three wkjudas entries (GBPUSD LONG, USDJPY SHORT, NZDUSD SHORT) and the two rizzy5m entries (AUDUSD SHORT, NZDUSD SHORT) that fall outside your defined session — that's 5 of 10 live trades. Of those, 4 are closed losses and 1 is open/rejected, so you would have avoided at least 3 confirmed losses and likely improved the window's win rate from 2/8 (25%) to 2/5 (40%), a +15pp shift, with a modest PnL gain from skipping losing trades. The remaining rizzy7m and one rizzy5m trade (GBPUSD SHORT WIN) would have been unaffected, so no wins are sacrificed. OVER-TIME PROJECTION: Over 3–6 months, this filter could lift win rate by 8–12pp if the backtest's +10.3pp holds, but the sample (n=126) is small and likely overfit to a specific market regime (e.g., low- 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: W7221660170
Cites:
Cited by:
Related to: