MODEL ADOPTION #4600: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.5% to 35.6% — E8 Intelligence Research
- 1Independent Researcher, United Kingdom
Abstract
DECISION: REJECT ELEMENT: No single rule survives — the 6-confirmation filter is a statistical artifact, not an E8-geometry-compatible edge. EXPECTED IMPACT: +0.0pp win-rate in live conditions; likely negative profit due to 10–20% trade-frequency loss without proven R-multiple gain. The +4.0pp backtest is overfit to a 922-trade sample and ignores that filtered trades may have larger average losses when they fail (early breakouts often have tighter stops). RISK: Filter delays entries into worse prices on fast rizzy moves, systematically capping TP2 capture on trending days; also removes low-confirmation winners that currently contribute to absolute PnL. The three rejected open trades are unresolved — citing them as avoided drawdown is survivorship bias. TEST: Must pass a 30-day shadow replay on the exact live signal stream (rizzy5m/7m, wkjudas) with 200+ filtered vs 200+ unfiltered trades, requiring ≥3pp win-rate improvement AND ≥0.0R average R-multiple advantage AND no increase
Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
Related
- 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 #4470: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.5% to 33.0% — E8 Intelligence Research
- MODEL ADOPTION #4177: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.6% to 38.3% — E8 Intelligence Research
- MODEL ADOPTION #4602: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.6% to 35.7% — E8 Intelligence Research
- MODEL ADOPTION #4626: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.2% to 37.3% — E8 Intelligence Research
BibTeX
@misc{caldin2026model,
title = {{MODEL ADOPTION #4600: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.5% to 35.6% — E8 Intelligence Research}},
author = {Andrew Stewart Caldin},
howpublished = {Zenodo},
year = {2026},
month = oct,
doi = {10.5281/zenodo.23587191},
url = {https://zenodo.org/records/23587191},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - MODEL ADOPTION #4600: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.5% to 35.6% — E8 Intelligence Research
AU - Andrew Stewart Caldin
PY - 2026
DA - 2026/10/23
PB - Zenodo
DO - 10.5281/zenodo.23587191
UR - https://zenodo.org/records/23587191
AB - DECISION: REJECT ELEMENT: No single rule survives — the 6-confirmation filter is a statistical artifact, not an E8-geometry-compatible edge. EXPECTED IMPACT: +0.0pp win-rate in live conditions; likely negative profit due to 10–20% trade-frequency loss without proven R-multiple gain. The +4.0pp backtest is overfit to a 922-trade sample and ignores that filtered trades may have larger average losses when they fail (early breakouts often have tighter stops). RISK: Filter delays entries into worse prices on fast rizzy moves, systematically capping TP2 capture on trending days; also removes low-confirmation winners that currently contribute to absolute PnL. The three rejected open trades are unresolved — citing them as avoided drawdown is survivorship bias. TEST: Must pass a 30-day shadow replay on the exact live signal stream (rizzy5m/7m, wkjudas) with 200+ filtered vs 200+ unfiltered trades, requiring ≥3pp win-rate improvement AND ≥0.0R average R-multiple advantage AND no increase Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
ER -