Enhancing stock market anomalies with machine learning
- We examine the predictability of 299 capital market anomalies enhanced by 30 machine learning approaches and over 250 models in a dataset with more than 500 million firm-month anomaly observations. We find significant monthly (out-of-sample) returns of around 1.8–2.0%, and over 80% of the models yield returns equal to or larger than our linearly constructed baseline factor. For the best performing models, the risk-adjusted returns are significant across alternative asset pricing models, considering transaction costs with round-trip costs of up to 2% and including only anomalies after publication. Our results indicate that non-linear models can reveal market inefficiencies (mispricing) that are hard to conciliate with risk-based explanations.
Author: | Vitor AzevedoORCiD, Christopher R. Hoegner |
---|---|
URN: | urn:nbn:de:hbz:386-kluedo-78712 |
DOI: | https://doi.org/10.1007/s11156-022-01099-z |
ISSN: | 1573-7179 |
Parent Title (English): | Review of Quantitative Finance and Accounting |
Publisher: | Springer Nature - Springer |
Document Type: | Article |
Language of publication: | English |
Date of Publication (online): | 2024/03/25 |
Year of first Publication: | 2022 |
Publishing Institution: | Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau |
Date of the Publication (Server): | 2024/03/25 |
Issue: | 60 |
Page Number: | 36 |
First Page: | 195 |
Last Page: | 230 |
Source: | https://link.springer.com/article/10.1007/s11156-022-01099-z |
Faculties / Organisational entities: | Kaiserslautern - Fachbereich Wirtschaftswissenschaften |
DDC-Cassification: | 3 Sozialwissenschaften / 330 Wirtschaft |
Collections: | Open-Access-Publikationsfonds |
Licence (German): | Zweitveröffentlichung |