LAB #4091 PROMISING: 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=1825) SAME-WINDOW EFFECT: Applying the pool density ≥90 filter would have excluded most of the wkjudas and rizzy5m entries above, as these were taken during low-density or fragmented liquidity windows (evidenced by the cluster of losses on 2026-08-27 and 2026-09-01). Specifically, the GBPUSD LONG, USDJPY SHORT, NZDUSD SHORT (wkjudas), and the three rizzy5m losses would likely have been filtered out — removing 5 of the 7 losing trades. The two wins (GBPUSD SHORT rizzy5m, EURUSD LONG rizzy7m) may or may not survive depending on their pool density at entry; if they survive, the window PnL improves from roughly −3.5R to near +1.5R, a swing of ~5R. The +1.5pp win-rate gain in backtest is directionally consistent with this live sample, though n is small and the effect is concentrated in loss avoidance rather than new wins. OVER-TI 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: W7222091539
Cites:
Cited by:
Related to: