LAB #3842 NEUTRAL: 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=1802) SAME-WINDOW EFFECT: Applying a minimum-confirmation filter of ≥5 would have eliminated the two rizzy5m entries (AUDUSD SHORT and NZDUSD SHORT) that are currently open or closed at a loss, plus the XAUUSD SHORT (also a loss). That removes 3 of 10 trades, all of which were losers in this window, leaving 7 trades with 2 wins and 5 losses — a raw win rate of ~28.6% vs. the actual 20% (2/10). PnL impact is positive but modest: you avoid three losing trades, but you also lose the chance for any future winners among those filtered signals; net expected PnL delta in this tiny sample is roughly +0.5R to +1.0R, not a game-changer. OVER-TIME PROJECTION: Over 3–6 months, a 1.5pp win-rate gain (32.5%→34.0%) on n=1802 is statistically weak (z≈1.1, p≈0.27) — likely within noise. The filter reduces trade frequency (fewer entries), which Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com