Society & Economicspreprint2026-08-18

LAB #1144 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.7% to 33.3% (+1.6pp, — E8 Intelligence Research

Open access0 citations

Abstract

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 5 — improves win rate from 31.7% to 33.3% (+1.6pp, n=1329) SAME-WINDOW EFFECT: Applying the min confirmations >= 5 filter to the live trade window would have rejected the EURUSD SHORT via rizzy5m (entry=1.13594) and the XAUUSD SHORT via rizzy5m (entry=4100.865), as these likely had fewer than 5 confirmations at entry. The EURUSD SHORT via rizzy (entry=1.13704, CLOSED/LOSS) might also be affected depending on its confirmation count. Removing these low-confidence entries could have avoided the EURUSD loss and the XAUUSD rejection, potentially improving the live win rate from ~50% (3 wins, 1 loss, 5 rejections) to ~60% (3 wins, 0 losses), with a small positive PnL delta from avoiding the loss. OVER-TIME PROJECTION: Over 3-6 months, this filter is expected to increase win rate by ~1.6pp as seen in the backtest, but it will also reduce trade frequency by filtering out borderline setu 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 2026-08-18

Authors: Andrew Stewart Caldin