The Promises and Pitfalls of Machine Learning for Predicting Stock Returns

42 Pages Posted: 27 Mar 2020

See all articles by Edward Leung

Edward Leung

Invesco

Harald Lohre

Invesco; Centre for Endowment Asset Management, Cambridge Judge Business School, University of Cambridge; Centre for Financial Econometrics, Asset Markets and Macroeconomic Policy, Lancaster University Management School

David Mischlich

Invesco

Yifei Shea

Invesco

Maximilian Stroh

Quoniam Asset Management

Date Written: March 1, 2020

Abstract

Recent research suggests that machine learning models dominate traditional linear models in predicting cross-sectional stock returns. Indeed, we confirm this finding when predicting one-month forward looking returns based on a set of common equity factors, including predictors such as short-term reversal. Despite this statistical advantage of machine learning model predictions, we demonstrate economic gains to be more limited and critically dependent on the ability to take risk and implement trades efficiently. Unlike traditional models, machine-learning models have struggled less over the last decade in discerning valuable predictions from cross-sectional equity characteristics.

Keywords: Machine Learning, Data Science, Interpretable Machine Learning, Return Prediction, Cross-Section of Stock Returns, Gradient Boosting, Factor Investing

JEL Classification: G11, G12, G14, G15, G17

Suggested Citation

Leung, Edward and Lohre, Harald and Mischlich, David and Shea, Yifei and Stroh, Maximilian, The Promises and Pitfalls of Machine Learning for Predicting Stock Returns (March 1, 2020). Available at SSRN: https://ssrn.com/abstract=3546725 or http://dx.doi.org/10.2139/ssrn.3546725

Edward Leung

Invesco ( email )

An der Welle 5
Frankfurt am Main, 60322
Germany

Harald Lohre

Invesco ( email )

An der Welle 5
Frankfurt am Main, 60322
Germany

HOME PAGE: http://www.de.invesco.com/portal/site/de-de/home/ueber-uns/invesco-quantitative-strategies/

Centre for Endowment Asset Management, Cambridge Judge Business School, University of Cambridge

Cambridge
United Kingdom

HOME PAGE: http://https://www.jbs.cam.ac.uk/faculty-research/centres/ceam/

Centre for Financial Econometrics, Asset Markets and Macroeconomic Policy, Lancaster University Management School

Bailrigg
Lancaster LA1 4YX
United Kingdom

HOME PAGE: http://www.lancaster.ac.uk/lums/research/research-centres/financial-econometrics/

David Mischlich

Invesco ( email )

An der Welle 5
Frankfurt am Main, 60322
Germany

Yifei Shea

Invesco

100 Federal St
28th floor
Boston, MA MA 02110
United States

Maximilian Stroh (Contact Author)

Quoniam Asset Management ( email )

Frankfurt
Germany

HOME PAGE: http://www.quoniam.com

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
211
Abstract Views
856
rank
157,520
PlumX Metrics