Can machine learning be helpful to asset management – and if so, how? Asset markets fundamentally differ from many of the environments in which machine learning has enjoyed success, and research into machine learning for asset management is just beginning.
In this Alternative Thinking, we discuss the crucial points for understanding the current state of machine learning in the practice of asset management:
- How machine learning attempts to solve difficult problems and how it differs from traditional computer programming.
- Why finance poses unique challenges even for the most powerful machine learning programs
- Early research evidence hints that machine learning tools can potentially improve investment portfolios
The application of machine learning techniques is a natural evolution for investment research, and one that will continue to be explored.
About the Portfolio Solutions Group
The Portfolio Solutions Group (PSG) aims to help AQR clients achieve better portfolio outcomes and provide unique insights to the broader investment community.
We thank Bryan Kelly, Ronen Israel and Tobias Moskowitz for their work on this paper. We also thank Gregor Andrade, Pete Hecht, Antti Ilmanen, Michael Katz, Lasse Pedersen and Dan Villalon for their helpful comments.