LAB #888 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.5% to 33.1% (+1.5pp, — E8 Intelligence Research

Abstract

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 5 — improves win rate from 31.5% to 33.1% (+1.5pp, n=1315) SAME-WINDOW EFFECT: Applying a minimum of 5 confirmations would have rejected the EURUSD SHORT (loss) and the GBPUSD LONG (loss), removing two losing trades from the window. It would also have rejected the GBPUSD SHORT (currently rejected/open) and the XAUUSD SHORT (rejected/open), but those are already not live wins. The net effect on this small sample is removing two losses, which would have improved the window's win rate from 5 wins / 10 total = 50% to 5 wins / 8 total = 62.5%, a +12.5pp improvement. However, this is a tiny sample (n=10) and the backtest's +1.5pp gain is far more reliable. OVER-TIME PROJECTION: Over 3-6 months, this filter should reduce false signals from low-conviction setups, lifting win rate by approximately 1-2pp as seen in the backtest. The primary risk is that it may also reject some genuine win Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com