LAB #1288 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.7% to 41.2% (+9.5pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 6 — improves win rate from 31.7% to 41.2% (+9.5pp, n=335) SAME-WINDOW EFFECT: Applying a minimum 6 confirmations filter would have rejected the EURUSD SHORT via rizzy5m (entry=1.13594, CLOSED/open) and the NZDUSD LONG via wkjudas (entry=0.57702, REJECTED/open) — both had fewer than 6 confirmations at entry. The EURUSD SHORT is still open, so its fate is unknown, but the NZDUSD LONG was already rejected, so no change there. The net effect on the current window is negligible — only one trade potentially removed, and its outcome is unresolved. The win-rate improvement from 31.7% to 41.2% in backtests (+9.5pp) is statistically significant (n=335), but the live sample here is too small to confirm. OVER-TIME PROJECTION: Over 3-6 months, this filter should reduce false signals from low-conviction setups, lifting win rate by ~8-10pp as seen in backtests. However, it will also cut total Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com