LAB #3993 NEUTRAL: LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 32.5% to 34.0% (+1.5pp, — E8 Intelligence Research

Abstract

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=1814) SAME-WINDOW EFFECT: Applying a min-5-confirmations filter would have rejected the two rizzy5m entries (AUDUSD SHORT and NZDUSD SHORT) that were already flagged as REJECTED or CLOSED/LOSS, plus the XAUUSD SHORT (CLOSED/LOSS). That removes 3 losing/neutral trades from the 10-trade window, leaving 7 trades with 2 wins and 1 open — a raw win-rate improvement from ~22% to ~29% on closed trades, but the sample is tiny and the open NZDUSD positions (wkjudas) are unaffected. PnL delta is positive but marginal, likely +0.2–0.4% over this window, driven mostly by avoiding the XAUUSD loss. OVER-TIME PROJECTION: Over 3–6 months, the +1.5pp win-rate gain (32.5%→34.0%) is statistically weak (n=1814, p≈0.08) and may not persist out-of-sample. The filter reduces trade frequency by ~15–20%, which lowers total gross PnL even if win rate r Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com