Machine Learning Classification and Portfolio Construction: Does the Loss Function Matter?

Yang Bai and Kuntara Pukthuanthong

Papers from arXiv.org

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 1.83 for classification and 1.11 for regression. This outperformance persists in multiclass settings, 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 sharper and more precise separation of return deciles.

Date: 2021-08, Revised 2026-06
New Economics Papers: this item is included in nep-big, nep-cmp, nep-fmk and nep-isf
References: Add references at CitEc
Citations:

Downloads: (external link)
https://arxiv.org/pdf/2108.02283 Latest version (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:arx:papers:2108.02283

Access Statistics for this paper

More papers in Papers from arXiv.org
Bibliographic data for series maintained by arXiv administrators ().