Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/309268 
Year of Publication: 
2022
Citation: 
[Journal:] OR Spectrum [ISSN:] 1436-6304 [Volume:] 45 [Issue:] 1 [Publisher:] Springer [Place:] Berlin, Heidelberg [Year:] 2022 [Pages:] 289-323
Publisher: 
Springer, Berlin, Heidelberg
Abstract: 
We compare the performance of the linear regression model, which is the current standard in science and practice for cross-sectional stock return forecasting, with that of machine learning methods, i.e., penalized linear models, support vector regression, random forests, gradient boosted trees and neural networks. Our analysis is based on monthly data on nearly 12,000 individual stocks from 16 European economies over almost 30 years from 1990 to 2019. We find that the prediction of stock returns can be decisively improved through machine learning methods. The outperformance of individual (combined) machine learning models over the benchmark model is approximately 0.6% (0.7%) per month for the full cross-section of stocks. Furthermore, we find no model breakdowns, which suggests that investors do not incur additional risk from using machine learning methods compared to the traditional benchmark approach. Additionally, the superior performance of machine learning models is not due to substantially higher portfolio turnover. Further analyses suggest that machine learning models generate their added value particularly in bear markets when the average investor tends to lose money. Our results indicate that future research and practice should make more intensive use of machine learning techniques with respect to stock return prediction.
Subjects: 
Machine learning
Finance
Stock return prediction
Persistent Identifier of the first edition: 
Creative Commons License: 
cc-by Logo
Document Type: 
Article
Document Version: 
Published Version

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.