Financial Analysts Journal· 2026Q1
Machine Learning Classification and Portfolio Construction: Does the Loss Function Matter?
- 1citations
- Q1SCImago
- 2026year
Short summary
Classification-based machine learning models yield a 2.08 annualized Sharpe ratio in portfolio construction, outperforming regression models (1.39 Sharpe ratio).
AI-generated from the title and abstract; the full text is not read.
Key points
- Classification machine learning models achieved a 2.08 annualized Sharpe ratio in portfolio construction, versus 1.39 for regression models.
- A stacking ensemble of gradient boosted tree, random forest, and neural network was used.
- Classification's outperformance increased with class granularity and persisted after transaction costs.
- Spanning tests showed classification alphas remained large when controlling for regression, while regression alphas shrank when controlling for classification.
AI-generated from the title and abstract; the full text is not read.
Abstract
Classification outperforms regression across matched machine learning models in portfolio construction. A stacking ensemble of gradient boosted tree, random forest, and neural network yields a value-weighted annualized Sharpe ratio of 2.08 for classification and 1.39 for regression. This outperformance strengthens with class granularity and persists across subsamples and after transaction costs. Spanning tests show that classification retains economically large alphas after we control for regression, whereas regression alphas shrink substantially once we control for classification. These results indicate that classification extracts more return information than matched regression. Our diagnostics trace classification’s advantage to more precise separation of return deciles.
The authors' abstract, as published at the source. Financial Analysts Journal, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Management Science and Operations Research
Management Science and Operations ResearchDecision Sciences