MODEL ADOPTION #4385: REJECT — LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.6% to 33. — E8 Intelligence Research
- 1Independent Researcher, United Kingdom
Abstract
DECISION: REJECT ELEMENT: No single rule survives — the pool density ≥90 filter is a statistical artifact, not an E8-geometry-compatible edge. EXPECTED IMPACT: The +1.4pp win-rate gain (n=1903) is within noise for a binary filter; over 3–6 months, it likely reduces trade count by 10–20% while cutting only ~1 in 70 trades as a net loser. Net PnL improvement is near zero after slippage and missed opportunities. The wkjudas exclusion in the 10-trade window is anecdotal — those losses were not density-driven but timing-driven (E8 rhythm violation). RISK: The filter is regime-correlated — high pool density often coincides with trending conditions; in choppy/mean-reverting regimes, density drops but FADE setups remain valid. Applying this filter would suppress exactly those trades, degrading the model's adaptability. Also, live pool density computation may differ from backtest (lookback window, data feed), causing silent divergence. TEST: Before any reconsideration, run a 12-month ro
Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
Related
- MODEL ADOPTION #4473: REJECT — LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.5% to 33. — E8 Intelligence Research
- MODEL ADOPTION #4606: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.6% to 35.8% — E8 Intelligence Research
- MODEL ADOPTION #4136: REJECT — LEDGER BENCH: Apply filter: Phase distance TIGHT (<=2deg) — improves win rate from 32.6% t — E8 Intelligence Research
- MODEL ADOPTION #4470: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.5% to 33.0% — E8 Intelligence Research
- MODEL ADOPTION #4600: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.5% to 35.6% — E8 Intelligence Research
BibTeX
@misc{caldin2026model,
title = {{MODEL ADOPTION #4385: REJECT — LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.6% to 33. — E8 Intelligence Research}},
author = {Andrew Stewart Caldin},
howpublished = {Zenodo},
year = {2026},
month = oct,
doi = {10.5281/zenodo.23465358},
url = {https://zenodo.org/records/23465358},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - MODEL ADOPTION #4385: REJECT — LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.6% to 33. — E8 Intelligence Research
AU - Andrew Stewart Caldin
PY - 2026
DA - 2026/10/19
PB - Zenodo
DO - 10.5281/zenodo.23465358
UR - https://zenodo.org/records/23465358
AB - DECISION: REJECT ELEMENT: No single rule survives — the pool density ≥90 filter is a statistical artifact, not an E8-geometry-compatible edge. EXPECTED IMPACT: The +1.4pp win-rate gain (n=1903) is within noise for a binary filter; over 3–6 months, it likely reduces trade count by 10–20% while cutting only ~1 in 70 trades as a net loser. Net PnL improvement is near zero after slippage and missed opportunities. The wkjudas exclusion in the 10-trade window is anecdotal — those losses were not density-driven but timing-driven (E8 rhythm violation). RISK: The filter is regime-correlated — high pool density often coincides with trending conditions; in choppy/mean-reverting regimes, density drops but FADE setups remain valid. Applying this filter would suppress exactly those trades, degrading the model's adaptability. Also, live pool density computation may differ from backtest (lookback window, data feed), causing silent divergence. TEST: Before any reconsideration, run a 12-month ro Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
ER -