LAB #2050 NEUTRAL: LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 32.0% to 33.6% (+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 32.0% to 33.6% (+1.6pp, n=1353) SAME-WINDOW EFFECT: Applying a minimum of 5 confirmations would have filtered out the weakest entries in your live window. Looking at the 10 trades listed, the three XAUUSD SHORTs (all losses) and the GBPUSD SHORT (loss) likely had lower confirmation counts — if filtered, you'd remove 4 losses while keeping 4 wins and 1 open (USDJPY), shifting the closed win rate from 4/9 (44%) to 4/5 (80%). However, the AUDUSD LONG and USDCAD SHORT wins may also have had 4 confirmations, so the actual delta is uncertain; worst case you remove 2 wins and 4 losses, improving win rate to 2/4 (50%) but cutting sample size drastically. PnL impact is positive if the filter targets the XAUUSD cluster specifically, but negative if it kills high-quality counter-trend wins. OVER-TIME PROJECTION: Over 3-6 months, a +1.6pp win-rate gain on 1,353 tr Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com