LAB #3900 NEUTRAL: LEDGER BENCH: Apply filter: Quarterly phase = MANIPULATION — improves win rate from 32.5% to 33.3% ( — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Quarterly phase = MANIPULATION — improves win rate from 32.5% to 33.3% (+0.8pp, n=1446) SAME-WINDOW EFFECT: Applying the MANIPULATION-phase filter to the current 10-trade window would have blocked trades that opened during that phase. Based on the backtest's +0.8pp win-rate lift, roughly 1–2 of the 10 trades would be filtered out, likely removing one of the losses (e.g., the XAUUSD or NZDUSD shorts). Expected PnL delta is small but positive — perhaps +0.1% to +0.3% on the window, assuming the filter does not accidentally remove a winner. The open/rejected AUDUSD short would likely survive, so no major structural change. OVER-TIME PROJECTION: Over 3–6 months, a +0.8pp win-rate gain on ~1,446 trades is statistically marginal (p≈0.15–0.2), and likely within noise. The filter may be capturing a regime-specific quirk (e.g., a particular quarter's manipulation pattern) that decays as market microstructure Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com