LAB #3995 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 32.5% to 34.0% (+1.5pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 5 — improves win rate from 32.5% to 34.0% (+1.5pp, n=1813) SAME-WINDOW EFFECT: Over the current 10-trade window, applying a minimum-5-confirmation filter would have rejected the two `rizzy5m` entries (AUDUSD SHORT and NZDUSD SHORT) and the one `rizzy7m` EURJPY LONG, as these likely entered before 5 confirmations. Of those three, only the NZDUSD SHORT closed as a loss; the other two are still open/rejected, so the immediate win-rate impact is marginal (removing one loss from a 2W/5L/3open sample would shift win rate from ~28.6% to ~33.3% on closed trades). PnL delta is negligible because the rejected AUDUSD trade is still open and the EURJPY loss would have been avoided, but the sample is too small to attribute significance. OVER-TIME PROJECTION: Over 3–6 months, the +1.5pp win-rate improvement (n=1813) suggests a modest but real edge from filtering out low-confidence early entri Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com