LAB #3915 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.5% to 38.2% (+5.7pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 6 — improves win rate from 32.5% to 38.2% (+5.7pp, n=812) SAME-WINDOW EFFECT: Applying the ≥6 confirmations filter would have blocked the two `rizzy5m` entries (AUDUSD SHORT and NZDUSD SHORT) that fired on 2026-08-27, both of which are currently open or closed at a loss. It would also have blocked the `rizzy5m` XAUUSD SHORT (loss) and the `rizzy5m` GBPUSD SHORT (win) from 2026-08-26, netting out to removing 2 losses and 1 win from the window. That shifts the live window from 3W/5L (37.5%) to 2W/3L (40%) — a small positive tilt, but the sample is too thin to attribute the +5.7pp backtest gain to this specific filter alone. OVER-TIME PROJECTION: Over 3–6 months, a minimum-confirmation filter should reduce false entries from low-timeframe noise, likely lifting win rate by 3–6pp as seen in backtest. However, the risk is that it also removes high-momentum breakouts that only confirm Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com