LAB #2117 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.0% to 42.2% (+10.2pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 6 — improves win rate from 32.0% to 42.2% (+10.2pp, n=360) SAME-WINDOW EFFECT: Applying a minimum-6-confirmation filter would have blocked the XAUUSD SHORT at 4048.74 (loss) and the XAUUSD SHORT at 4051.79 (loss) — both entered on rizzy5m with fewer than 6 confirmations. It would also have blocked the EURJPY SHORT at 184.144 (win), so you'd lose that gain. Net effect on the 10-trade window: 2 losses removed, 1 win removed — PnL improves by roughly +1.5R to +2R (assuming typical risk/reward), and win rate in this sample rises from 5/10 to 4/7 (57% vs 50%). The open USDJPY trade is unaffected (wkjudas, not rizzy5m). OVER-TIME PROJECTION: Over 3–6 months, the filter should reduce false entries from low-conviction rizzy5m signals, which historically have a sub-40% win rate. The backtest gain (+10.2pp) is plausible but likely overfitted to a specific regime — confirmation counts ofte Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com