IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 7 — improves win rate from 32.2% to 48.1% (+15.9pp, n=27) SAME-WINDOW EFFECT: Applying a minimum of 7 confirmations would have filtered out all four REJECTED/open trades (USDCHF, EURJPY, AUDUSD long, and the AUDUSD short that closed as a loss — wait, that one had 7m but likely fewer confirmations; regardless, the three open/rejected longs and the EURJPY short would be excluded). That removes 3 open positions and 1 loss, leaving the 4 closed wins and 2 closed losses (GBPUSD long, USDJPY short) — a live win rate of 4/6 = 66.7% vs. the current 4/10 = 40% including rejects. PnL delta is positive but small in absolute terms since the rejected trades never triggered SL/TP; the main benefit is avoiding capital lockup and emotional noise from unconfirmed entries. The backtest's +15.9pp is directionally consistent but overstated here because the live window has only 6 qualifying trades. Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
No takes yet. Share an insight, caveat, or question.
Andrew Stewart Caldin (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: