Deep Learning for Finance: Deep Portfolios

15 Pages Posted: 14 Sep 2016  

J.B. Heaton

Bartlit Beck Herman Palenchar & Scott LLP

Nick Polson

University of Chicago - Booth School of Business

Jan Hendrik Witte

University of Oxford - Mathematical Institute

Date Written: September 5, 2016

Abstract

We explore the use of deep learning hierarchical models for problems in financial prediction and classification. Financial prediction problems – such as those presented in designing and pricing securities, constructing portfolios, and risk management – often involve large data sets with complex data interactions that currently are difficult or impossible to specify in a full economic model. Applying deep learning methods to these problems can produce more useful results than standard methods in finance. In particular, deep learning can detect and exploit interactions in the data that are, at least currently, invisible to any existing financial economic theory.

Keywords: Deep Learning, Machine Learning, Big Data, Artificial Intelligence, Finance, Asset Pricing, Volatility, Deep Frontier

JEL Classification: C58, G11, G12

Suggested Citation

Heaton, J.B. and Polson, Nick and Witte, Jan Hendrik, Deep Learning for Finance: Deep Portfolios (September 5, 2016). Available at SSRN: https://ssrn.com/abstract=2838013 or http://dx.doi.org/10.2139/ssrn.2838013

J.B. Heaton

Bartlit Beck Herman Palenchar & Scott LLP ( email )

Courthouse Place
54 West Hubbard Street
Chicago, IL 60610
United States
312-494-4425 (Phone)
312-494-4440 (Fax)

Nick Polson

University of Chicago - Booth School of Business ( email )

5807 S. Woodlawn Avenue
Chicago, IL 60637
United States
773-702-7513 (Phone)
773-702-0458 (Fax)

Jan Hendrik Witte (Contact Author)

University of Oxford - Mathematical Institute ( email )

United Kingdom

Paper statistics

Downloads
2,010
Rank
5,319
Abstract Views
4,431