Predicting European stock returns using machine learning

Antonio Marsi

SN Business & Economics, 2023, vol. 3, issue 7, 1-25

Abstract: Abstract This paper examines the predictability of equity returns in the European stock market through the use of several machine learning techniques. Specifically, we focus on the monthly returns of equities included in the EURO STOXX 50 index from 1994 to 2018, with a large set of stock-level characteristics interacted with macroeconomic variables as predictors. Unlike prior studies that used US data and larger samples, we find that linear methods perform better than highly non-linear ones in terms of predictability. However, the overall predictive ability of machine learning algorithms remains relatively low, indicating that equity returns in our sample are highly unpredictable, in line with the efficient market hypothesis. Our findings suggest that while machine learning may offer some predictive power, it is not a panacea for predicting equity returns in the European stock market.

Keywords: Machine learning; Stock returns predictability; Forecasting; European stock market (search for similar items in EconPapers)
JEL-codes: C52 C55 C58 G0 G1 G17 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s43546-023-00487-4 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:spr:snbeco:v:3:y:2023:i:7:d:10.1007_s43546-023-00487-4

Ordering information: This journal article can be ordered from
https://www.springer.com/journal/43546

DOI: 10.1007/s43546-023-00487-4

Access Statistics for this article

SN Business & Economics is currently edited by Gino D'Oca

More articles in SN Business & Economics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().