MODEL ADOPTION #4465: REJECT — LEDGER BENCH: Apply filter: Session = OFF_SESSION — improves win rate from 31.5% to 41.9% — E8 Intelligence Research
- 1Independent Researcher, United Kingdom
Abstract
DECISION: REJECT ELEMENT: No element survives — OFF_SESSION filter is a statistical artifact, not an E8-geometry edge. EXPECTED IMPACT: Win-rate gain is likely regression to the mean (n=129, +10.3pp driven by 2–3 favorable weeks). Filtering by session alone ignores the model's core rhythm logic — it would blind the executor to legitimate off-session FADE setups that align with Gods-Clock phase transitions, where liquidity gaps actually favor our polarity edge. Realized impact: likely −2–5% profit due to missed high-R Asian intervention moves, with no durable win-rate improvement beyond noise. RISK: (1) Overfitting to a small backtest window — the 41.9% figure collapses under walk-forward. (2) Removes news-driven off-session breakouts that occasionally produce 3–5R winners, capping upside. (3) Spread mechanism unverified — no data shows wider spreads caused the losses; could be random clustering. (4) Violates E8 principle: session is not a timing variable in the model's geometry;
Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
Related
- MODEL ADOPTION #4140: REJECT — LEDGER BENCH: Apply filter: Session = OFF_SESSION — improves win rate from 32.6% to 42.5% — E8 Intelligence Research
- MODEL ADOPTION #4171: REJECT — LEDGER BENCH: Apply filter: Session = LONDON_OPEN — improves win rate from 32.6% to 36.2% — E8 Intelligence Research
- MODEL ADOPTION #4639: REJECT — VIDEO SCOUT: ICT Concepts - London Session Raids 2:00am to 5:00am, New York Local Time — 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
BibTeX
@misc{caldin2026model,
title = {{MODEL ADOPTION #4465: REJECT — LEDGER BENCH: Apply filter: Session = OFF_SESSION — improves win rate from 31.5% to 41.9% — E8 Intelligence Research}},
author = {Andrew Stewart Caldin},
howpublished = {Zenodo},
year = {2026},
month = oct,
doi = {10.5281/zenodo.23526014},
url = {https://zenodo.org/records/23526014},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - MODEL ADOPTION #4465: REJECT — LEDGER BENCH: Apply filter: Session = OFF_SESSION — improves win rate from 31.5% to 41.9% — E8 Intelligence Research
AU - Andrew Stewart Caldin
PY - 2026
DA - 2026/10/21
PB - Zenodo
DO - 10.5281/zenodo.23526014
UR - https://zenodo.org/records/23526014
AB - DECISION: REJECT ELEMENT: No element survives — OFF_SESSION filter is a statistical artifact, not an E8-geometry edge. EXPECTED IMPACT: Win-rate gain is likely regression to the mean (n=129, +10.3pp driven by 2–3 favorable weeks). Filtering by session alone ignores the model's core rhythm logic — it would blind the executor to legitimate off-session FADE setups that align with Gods-Clock phase transitions, where liquidity gaps actually favor our polarity edge. Realized impact: likely −2–5% profit due to missed high-R Asian intervention moves, with no durable win-rate improvement beyond noise. RISK: (1) Overfitting to a small backtest window — the 41.9% figure collapses under walk-forward. (2) Removes news-driven off-session breakouts that occasionally produce 3–5R winners, capping upside. (3) Spread mechanism unverified — no data shows wider spreads caused the losses; could be random clustering. (4) Violates E8 principle: session is not a timing variable in the model's geometry; Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
ER -