LAB #1110 PROMISING: LEDGER BENCH: Apply filter: USDCHF SHORT — improves win rate from 31.7% to 61.2% (+29.5pp, n=165) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT — improves win rate from 31.7% to 61.2% (+29.5pp, n=165) SAME-WINDOW EFFECT: Over the current trade window, applying the USDCHF SHORT filter would have blocked the one USDCHF SHORT trade that was already a winner (rizzy5m entry=0.81212, CLOSED/WIN). This means the filter would have removed a profitable trade, reducing the win count by 1 and lowering the window's win rate slightly. The net PnL delta would be negative, as that trade contributed a gain. However, the filter's benefit is seen in the broader backtest (n=165), not in this small sample. OVER-TIME PROJECTION: Over 3-6 months, the filter could improve overall win rate by roughly 30 percentage points on USDCHF SHORT trades, as per the backtest. However, the risk is that the filter may be overfitted to the specific backtest period, and live market conditions (e.g., CHF strength shifts) could erode its edge. Additionally, blocking a Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com