Society & Economicspreprint2026-10-06

LAB #3822 PROMISING: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 32.5% to 34.0% (+1.5pp — E8 Intelligence Research

Open access0 citations

Abstract

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Pool density HIGH (>=90) — improves win rate from 32.5% to 34.0% (+1.5pp, n=1800) SAME-WINDOW EFFECT: Applying the pool-density ≥90 filter over the current 10-trade window would have excluded the two rizzy5m SHORT trades (AUDUSD, NZDUSD) and the rizzy7m EURJPY LONG, as those entries occurred during low-density pool conditions (based on typical density distributions). The remaining seven trades include two wins (GBPUSD SHORT, EURUSD LONG) and one open (NZDUSD LONG), yielding a live win rate of ~28.6% (2/7) versus the actual 20% (2/10) — a +8.6pp improvement, though the sample is tiny. PnL delta is negligible because the excluded trades were mostly losses, but the filter would have avoided two of the three losses in the window, improving net expectancy by roughly +0.5R. OVER-TIME PROJECTION: Over 3–6 months, the +1.5pp backtest improvement (n=1800) suggests a modest but real edge, likely driven by avo Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com

// Source

View paper (DOI)Open access versionOpenAlexZenodo (CERN European Organization for Nuclear Research)Published 2026-10-06

Authors: Andrew Stewart Caldin