LAB #2651 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.0% to 32.6% (+1.6pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 5 — improves win rate from 31.0% to 32.6% (+1.6pp, n=1413) SAME-WINDOW EFFECT: Applying a minimum of 5 confirmations would have filtered out the two trades with the weakest confluence signals. In the current window, the most likely candidates for rejection are the USDJPY SHORT (wkjudas, LOSS) and the XAUUSD SHORT on 2026-08-04 (rizzy5m, LOSS), both of which likely had fewer than 5 stacked confirmations at entry. Removing those two losses from the 10-trade sample would shift the record from 6W/4L to 6W/2L, improving the win rate from 60% to 75% and adding roughly +2.0R to PnL. However, this is a small sample and the filter may also have rejected one of the winners if its confirmation stack was borderline. OVER-TIME PROJECTION: Over 3–6 months, a 5-confirmation minimum should reduce noise entries and lift win rate by roughly 1–2pp, consistent with the backtest. The main risk is ov Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com