LAB #1059 NEUTRAL: LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.6% to 33.2% (+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 31.6% to 33.2% (+1.6pp, n=1323) **SAME-WINDOW EFFECT:** Applying a minimum of 5 confirmations would have filtered out the REJECTED/open trades (NZDUSD, XAUUSD, EURJPY, AUDUSD) and possibly the USDJPY SHORT (wkjudas, 1 confirmation). Among the closed trades, only EURUSD SHORT (loss) and USDCAD LONG (win) had ≥5 confirmations? — unclear from data. If the filter removed the loss from EURUSD SHORT but also the wins from USDCAD, GBPUSD, USDCHF, and USDJPY, net effect is ambiguous. Rough estimate: win rate could shift from ~60% (3 wins, 2 losses among closed) to ~50% (1 win, 1 loss) — a *decrease* of ~10pp, contradicting backtest. PnL likely negative due to losing profitable trades. **OVER-TIME PROJECTION:** Over 3–6 months, the filter may reduce noise but also cut high-frequency, low-confirmation winners (e.g., rizzy5m scalps). The backtest's +1.6pp win Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com