LAB #4130 NEUTRAL: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 32.6% to 34.1% (+1.5pp — E8 Intelligence Research
Year: 2026
Type: preprint
Abstract: IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Pool density HIGH (>=90) — improves win rate from 32.6% to 34.1% (+1.5pp, n=1832) SAME-WINDOW EFFECT: Applying a pool-density filter (>=90) would have excluded most of the trades listed above, as the live entries (rizzy5m/rizzy7m/wkjudas) do not carry pool-density metadata in this snapshot. If the filter had been active, the only trades potentially retained would be those with density >=90 — none are identifiable here, so the immediate effect is a near-total trade suppression. That would have avoided the 4 losses and 1 open, but also skipped the 2 wins, yielding a net PnL change close to zero or slightly negative due to lost winning trades. The +1.5pp backtest gain is not visible in this small, density-unlabeled sample, so no live confirmation is possible from this window. OVER-TIME PROJECTION: Over 3–6 months, a density>=90 filter would likely reduce trade frequency substantially (possibly 40–60% f Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
Author: Caldin, Andrew Stewart
Language: English
Subfield: Finance
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7222446474
Cites:
Cited by:
Related to: