LAB #4470 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.5% to 33.0% (+1.4pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 5 — improves win rate from 31.5% to 33.0% (+1.4pp, n=1907) SAME-WINDOW EFFECT: Applying a minimum of 5 confirmations would have filtered out the two REJECTED/open trades (EURJPY SHORT and AUDUSD LONG) — both of which are currently unresolved and not counted in the win-rate denominator. Among the 8 closed trades, none appear to have fewer than 5 confirmations (all show rizzy5m/7m or wkjudas entries with clear signals), so the live closed-trade record would be unchanged: 4 wins, 2 losses, 2 open. The +1.4pp win-rate improvement in backtest likely comes from removing low-confidence entries that never reached live status; in this window, the filter would only reduce exposure (two open positions removed) without altering realized PnL, yielding a neutral-to-slightly-positive effect on risk-adjusted returns. OVER-TIME PROJECTION: Over 3-6 months, requiring ≥5 confirmations should syste Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com