LAB #2854 NEUTRAL: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.1% to 32.7% (+1.6pp — E8 Intelligence Research
IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.1% to 32.7% (+1.6pp, n=1426) SAME-WINDOW EFFECT: Applying the pool density ≥90 filter would have excluded trades triggered during low-density windows. In the current 10-trade window, 4 trades (GBPUSD 08-07 11:35, USDCHF 08-07 10:30, GBPUSD 08-03 11:00, XAUUSD 07-31 11:20) likely fall below that threshold based on typical density patterns — removing 2 wins and 2 losses. Net PnL delta is roughly neutral (removing 2W/2L), but win rate on remaining trades would rise from 50% (5/10) to 60% (3/5) — consistent with the backtest direction but on tiny n. The rejected USDCHF trade would also be filtered, which is a positive since it never resolved. OVER-TIME PROJECTION: Over 3–6 months, the +1.6pp win-rate gain is modest but could compound if density correlates with regime stability. Risk: the filter reduces trade frequency (likely 15–25% fewer signals), wh Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
Authors
- Andrew Stewart Caldin
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-09-29
- DOI
- https://doi.org/10.5281/zenodo.23030803
- Primary Topic
- Intelligence, Security, War Strategy
- Type
- preprint