Pooling and winsorizing machine learning forecasts to predict stock returns with high-dimensional data

Erik Mekelburg and Jack Strauss

Journal of Empirical Finance, 2024, vol. 79, issue C

Abstract: We evaluate US market return predictability using a novel data set of several hundred ag- gregated firm-level characteristics. We apply LASSO, Elastic Net, Random Forest, Neural Net, Extreme Gradient Boosting, and Light Gradient Boosting Machine methods and find these models experience large prediction errors that lead to forecast failures. However, winsorizing and pooling machine learning model forecasts provides consistent out-of-sample predictability. To assess robustness, we apply machine learning methods to high-dimensional data for Canada, China, Germany and the UK as well as the Goyal–Welch data. All machine learning models we consider, except for the ensemble pooled methods, fail to significantly predict returns across our samples, highlighting the importance of pooling, evaluating additional economies, and the fragility of individual machine learning methods. Our results shed light on the sparsity versus density debate as the degree of sparsity and variable importance evolves over time.

Keywords: Machine learning; Out-of-sample predictability; Pooling; Ensembles; Return predictability (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0927539824000732
Full text for ScienceDirect subscribers only

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:eee:empfin:v:79:y:2024:i:c:s0927539824000732

DOI: 10.1016/j.jempfin.2024.101538

Access Statistics for this article

Journal of Empirical Finance is currently edited by R. T. Baillie, F. C. Palm, Th. J. Vermaelen and C. C. P. Wolff

More articles in Journal of Empirical Finance from Elsevier
Bibliographic data for series maintained by Catherine Liu ().