LAB #3985 NEUTRAL: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 32.5% to 34.0% (+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 32.5% to 34.0% (+1.5pp, n=1814) SAME-WINDOW EFFECT: Applying the pool-density filter (>=90) would have excluded trades triggered during low-density conditions. In the current window, the NZDUSD SHORT via wkjudas (entry 0.59214) and the AUDUSD SHORT via rizzy5m (rejected) likely fall into low-density pools — removing them would have avoided one open loss and one rejected signal. The remaining trades (e.g., GBPUSD WIN, EURUSD WIN) appear density-qualified, so the filter would have preserved wins while cutting at least one loss. Net effect: win rate in this small sample would improve from ~33% (2/6 closed) to ~40% (2/5 closed), with a modest PnL gain from avoiding the NZDUSD loss. OVER-TIME PROJECTION: Over 3–6 months, a +1.5pp win-rate gain from n=1814 is statistically marginal (p≈0.08) and may not replicate live due to regime shifts. The filter risks 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: W7221458953
Cites:
Cited by:
Related to: