Robo-advising: Learning Investors' Risk Preferences via Portfolio Choices

39 Pages Posted: 6 Nov 2019 Last revised: 18 Nov 2019

See all articles by Humoud Alsabah

Humoud Alsabah

Columbia University

Agostino Capponi

Columbia University

Octavio Ruiz Lacedelli

Columbia University

Matt Stern

Columbia University - Department of Industrial Engineering and Operations Research (IEOR)

Date Written: November 16, 2019

Abstract

We introduce a reinforcement learning framework for retail robo-advising. The robo-advisor does not know the investor’s risk preference, but learns it over time by observing her portfolio choices in different market environments. We develop an exploration-exploitation algorithm which trades off costly solicitations of portfolio choices by the investor with autonomous trading decisions based on stale estimates of investor’s risk aversion. We show that the algorithm’s value function converges to the optimal value function of an omniscient robo-advisor over a number of periods that is polynomial in the state and action space. By correcting for the investor’s mistakes, the robo-advisor may outperform a stand-alone investor, regardless of the investor’s opportunity cost for making portfolio decisions.

Keywords: robo-advising, reinforcement learning, portfolio selection, probably approximately correct-Markov decision processes (PAC-MDP)

JEL Classification: D14, G02, G11

Suggested Citation

Alsabah, Humoud and Capponi, Agostino and Ruiz Lacedelli, Octavio and Stern, Matt, Robo-advising: Learning Investors' Risk Preferences via Portfolio Choices (November 16, 2019). Available at SSRN: https://ssrn.com/abstract=3228685 or http://dx.doi.org/10.2139/ssrn.3228685

Humoud Alsabah

Columbia University

S. W. Mudd Building
New York, NY 10027
United States

Agostino Capponi (Contact Author)

Columbia University ( email )

S. W. Mudd Building
New York, NY 10027
United States

Octavio Ruiz Lacedelli

Columbia University ( email )

116th and Broadway
New York, NY 10027
United States

Matt Stern

Columbia University - Department of Industrial Engineering and Operations Research (IEOR) ( email )

331 S.W. Mudd Building
500 West 120th Street
New York, NY 10027
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
58
Abstract Views
553
rank
373,819
PlumX Metrics