LAB #1892 NEUTRAL: LEDGER BENCH: Apply filter: SOLUSD LONG — improves win rate from 31.9% to 34.0% (+2.1pp, n=50) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: SOLUSD LONG — improves win rate from 31.9% to 34.0% (+2.1pp, n=50) SAME-WINDOW EFFECT: Applying a SOLUSD LONG-only filter would have excluded all 10 live trades in the window, since none are SOLUSD and none are LONG on SOL. This yields zero trade-level impact on the current set — no wins removed, no losses avoided. The +2.1pp win-rate improvement from the backtest (n=50) is statistically fragile (p≈0.3), and the live window shows no SOLUSD exposure to validate it. Expected PnL delta: $0, with no change to the 4W/5L outcome. OVER-TIME PROJECTION: Over 3-6 months, this filter would only affect future SOLUSD LONG entries, which are rare in your current strategy mix (0 in the last 30 days). If the backtest edge is real, it could add ~2pp win rate on a tiny subset of trades — negligible absolute PnL. Risk: overfitting to a small sample (n=50) with high variance; the filter may also block profitable SOLUS Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com