MODEL ADOPTION #4626: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.2% to 37.3% — E8 Intelligence Research
- 1Independent Researcher, United Kingdom
Abstract
DECISION: REJECT ELEMENT: No single rule survives — the ≥6 confirmation filter is a statistical artifact, not a geometric edge. E8 timing already encodes confirmation thresholds via Gods-Clock phase alignment; adding a fixed count filter would distort the FADE polarity entry window and reduce trade frequency without a proven PnL-per-trade gain. EXPECTED IMPACT: Win rate might rise 2–4pp in backtest, but absolute profit likely falls 15–25% due to fewer trades, and the unresolved three trades (USDCHF, EURJPY, AUDUSD) could easily flip the live delta negative if they win. No evidence that filtered-out early entries have worse R-multiple or MAE in live conditions — only a win-rate shift from a small n=871 sample. RISK: Overfitting to a regime with many false early signals; confirmation counts are broker-feed-latency dependent, so live vs backtest parity is unverified; rejecting fast breakouts that never reach 6 confirmations could miss the exact momentum spikes E8 FADE polarity is de
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 #4600: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.5% to 35.6% — 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
BibTeX
@misc{caldin2026model,
title = {{MODEL ADOPTION #4626: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.2% to 37.3% — E8 Intelligence Research}},
author = {Andrew Stewart Caldin},
howpublished = {Zenodo},
year = {2026},
month = oct,
doi = {10.5281/zenodo.23610246},
url = {https://zenodo.org/records/23610246},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - MODEL ADOPTION #4626: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.2% to 37.3% — E8 Intelligence Research
AU - Andrew Stewart Caldin
PY - 2026
DA - 2026/10/24
PB - Zenodo
DO - 10.5281/zenodo.23610246
UR - https://zenodo.org/records/23610246
AB - DECISION: REJECT ELEMENT: No single rule survives — the ≥6 confirmation filter is a statistical artifact, not a geometric edge. E8 timing already encodes confirmation thresholds via Gods-Clock phase alignment; adding a fixed count filter would distort the FADE polarity entry window and reduce trade frequency without a proven PnL-per-trade gain. EXPECTED IMPACT: Win rate might rise 2–4pp in backtest, but absolute profit likely falls 15–25% due to fewer trades, and the unresolved three trades (USDCHF, EURJPY, AUDUSD) could easily flip the live delta negative if they win. No evidence that filtered-out early entries have worse R-multiple or MAE in live conditions — only a win-rate shift from a small n=871 sample. RISK: Overfitting to a regime with many false early signals; confirmation counts are broker-feed-latency dependent, so live vs backtest parity is unverified; rejecting fast breakouts that never reach 6 confirmations could miss the exact momentum spikes E8 FADE polarity is de Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
ER -