SSRNML & AI Methods
Where Machine Learning Helps: Risk Timing, Trend Filtering, and an Untouched 2025-26 Holdout
Five pre-registered hypotheses about machine learning for volatility, drawdowns, trend filtering, stock ranking, and news failed validation on a 2025-26 holdout despite passing development tests.
Featured in No. 136 on 23 Oct 2026 · 4 days after release
- Released
- 19 Oct 2026
- First featured
- No. 136 · 23 Oct 2026
- Published in
- Not yet, as far as Semantic Scholar knows
- Fanfare
- 3 of 5
- Identifier
- SSRN 7623819
- Authors
- Prashant Malan
Citations and venue from Semantic Scholar (ODC-BY), refreshed weekly. Summary: Quant Letter (CC BY 4.0).