Published October 21, 2026 | Version v1

LAB #4494 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT @ OFF_SESSION with 6 conf — improves win rate from 31.6% to — E8 Intelligence Research

Authors/Creators

  • 1. Independent Researcher, United Kingdom

Description

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT @ OFF_SESSION with 6 conf — improves win rate from 31.6% to 66.7% (+35.0pp, n=6) SAME-WINDOW EFFECT: Over the current live window, no USDCHF SHORT trades appear in the list, so this filter would have changed nothing in the observed trades. The claimed improvement (+35.0pp win rate) is based on only n=6 backtest samples, which is statistically fragile — a single outcome flip changes the result by ~16.7pp. The live window shows no USDCHF SHORT entries at all, so the filter's immediate PnL delta is zero, but it would have suppressed any future USDCHF SHORTs during off-session with conf<6 — none occurred here. Net effect on the shown trades: nil. OVER-TIME PROJECTION: Over 3–6 months, this filter would likely reduce trade frequency on USDCHF SHORTs during off-session, potentially cutting losses but also missing winners. The 31.6%→66.7% jump is suspiciously large for a single-condition filte

Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com

Notes

ASC Watermark: ASC-1274690 | Published via Hermes E8 Intelligence Platform | e8intelligence.com

Files

ASC-1274690_e8_breakthrough.txt

Files (3.9 kB)

Name Size
md5:3793ea29c094fc6b7c5637f28201feb1
3.9 kB Preview Download