LAB #2327 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.5% to 33.1% (+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 31.5% to 33.1% (+1.6pp, n=1379) SAME-WINDOW EFFECT: Applying a minimum-5-confirmation filter to the live window above would have blocked the two rizzy5m XAUUSD shorts (entries at 4051.79 and 4066.35) and the GBPUSD short — all three were losses. It would also have blocked the AUDUSD long (a win) and the EURJPY long (a win), netting a change of −2 wins, +3 losses removed → net win count unchanged (from 4W/6L to 2W/3L), but PnL improves because the three removed losses likely outweighed the two removed wins in magnitude. The USDCAD win and USDJPY open would remain, so the immediate effect is a modest PnL gain, not a win-rate shift. OVER-TIME PROJECTION: Over 3–6 months, the +1.6pp win-rate gain is small but consistent with the hypothesis that low-confirmation signals are noise-driven. The risk is that you are also filtering out early entries on strong tr Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com