LAB #2205 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.9% to 33.5% (+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 31.9% to 33.5% (+1.6pp, n=1365) SAME-WINDOW EFFECT: Applying a minimum 5-confirmation filter would have eliminated the three XAUUSD SHORT entries (4048.74, 4051.79, 4066.35) — all closed as LOSSES — and likely the GBPUSD SHORT (1.34508, LOSS) if it entered before 5 confirmations. That removes 4 losing trades from the 10 shown, leaving the 4 wins and 1 open (USDJPY) intact, flipping the window from 4W/5L/1O to 4W/0L/1O. Win rate in the sample jumps from ~44% to 100% on closed trades, and PnL delta is strongly positive (removing ~4 losses at typical risk/reward). However, this is a tiny sample and the filter may also have blocked some winners in the broader backtest — the +1.6pp is the net effect, not a guarantee per trade. OVER-TIME PROJECTION: Over 3–6 months, a 5-confirmation filter should reduce noise entries triggered by early signal flicker, likely Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com