LAB #2625 PROMISING: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.0% to 32.6% (+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 31.0% to 32.6% (+1.6pp, n=1413) SAME-WINDOW EFFECT: Applying the pool density ≥90 filter to the 10 live trades above would have excluded trades lacking that density context. Based on the backtest, you'd expect roughly 1.6pp win-rate improvement, translating to ~0.16 additional wins in this small sample — likely flipping one borderline loss to a win (e.g., the GBPUSD SHORT on 08-03 or XAUUSD SHORT on 07-31). PnL delta would be modest, roughly +0.5R to +1.0R, but the sample is too small to confirm statistical significance. The filter would not have rejected any of the current winners, so downside risk in this window is minimal. OVER-TIME PROJECTION: Over 3–6 months, a +1.6pp win-rate gain on ~1,400 trades suggests ~22 additional wins, but this comes at the cost of reduced trade frequency — you'll skip lower-density setups that may include some winners. 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
- 2026-09-24
- DOI
- https://doi.org/10.5281/zenodo.22931125
- Primary Topic
- Competitive and Knowledge Intelligence
- Type
- preprint