Society & Economicspreprint2026-08-02

LAB #649 NEUTRAL: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 32.1% to 33.7% (+1.6pp — 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 32.1% to 33.7% (+1.6pp, n=1287) SAME-WINDOW EFFECT: Applying the Pool density HIGH (>=90) filter to the current live window would have rejected the EURJPY SHORT via fade_h4 (entry 186.016) and the AUDUSD SHORT via fade_h4 (entry 0.70029), both currently REJECTED/open. The filter would not have altered any of the closed trades, as none of them originated from pools with density below 90. The net effect on this small sample is neutral — no win-rate or PnL change, since the filtered trades were already non-performing in the live window. OVER-TIME PROJECTION: The backtest shows a modest +1.6pp win-rate improvement from 32.1% to 33.7% over 1287 samples, which is statistically significant but economically marginal. Over 3-6 months, this filter may reduce total trade count by roughly 10-15% (pools with density <90 tend to be less frequent), potentially lowe 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 2026-08-02

Authors: Andrew Stewart Caldin