LAB #2643 NEUTRAL: 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=1414) SAME-WINDOW EFFECT: Applying a minimum of 5 confirmations would have filtered out the two GBPUSD shorts (rizzy5m at 1.34407 and 1.34461) and the XAUUSD short (rizzy5m at 4048.74) if those entries had fewer than 5 confirmations at trigger time — but the live list shows those three closed as WIN/WIN/LOSS respectively. Removing the two wins and one loss would drop the live window win rate from 6/10 (60%) to 4/7 (57%), a net loss of 2 wins and 1 loss — so the +1.6pp backtest gain does not translate here; it would have reduced absolute wins by 2 while only removing 1 loss, worsening realized PnL in this specific window. OVER-TIME PROJECTION: Over 3–6 months, the filter likely reduces trade frequency by ~15–20% (based on the n=1414 backtest), and the +1.6pp win-rate gain is marginal and within noise for that sample size (p-val Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com