LAB #1939 NEUTRAL: LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.9% 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 31.9% to 33.6% (+1.6pp, n=1347) SAME-WINDOW EFFECT: Applying a minimum 5-confirmation filter would have eliminated the two rizzy5m entries with fewer confirmations (GBPUSD SHORT at 1.34508 and XAUUSD SHORT at 4051.79 — both losses). That removes 2 losing trades from the 9-trade window, shifting the live record from 4W/5L to 4W/3L — a win-rate jump from 44.4% to 57.1%. PnL delta is positive but modest, as the two removed losses were small; the bigger effect is variance reduction, not return magnification. OVER-TIME PROJECTION: Over 3–6 months, the +1.6pp backtest improvement is statistically thin (n=1347, p≈0.08) and likely driven by filtering out low-conviction noise entries that cluster around choppy conditions. Risk: the filter may also exclude early winners that trigger on strong momentum before 5 confirmations accumulate — potentially capping upsid Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com