Machine Learning for Stock Selection

Financial Analysts Journal, vol. 75, no. 3 (Third Quarter 2019)

35 Pages Posted: 4 Mar 2019 Last revised: 9 Aug 2019

See all articles by Keywan Rasekhschaffe

Keywan Rasekhschaffe

Gresham Investment Management, LLC

Robert Jones

Arwen Advisors

Date Written: February 8, 2019

Abstract

Machine learning is an increasingly important and controversial topic in quantitative finance. A lively debate persists as to whether machine learning techniques can be practical investment tools. Although machine learning algorithms can uncover subtle, contextual and non-linear relationships, overfitting poses a major challenge when trying to extract signals from noisy historical data. In this article, we describe some of the basic concepts surrounding machine leaning and provide a simple example of how investors can use machine learning techniques to forecast the cross-section of stock returns while limiting the risk of overfitting.

Keywords: Machine Learning, Return Prediction, Cross-Section of Returns, Gradient Boosting, SVM, AdaBoost, (Deep) Neural Networks, Feature Engineering, Fintech

JEL Classification: G10, G11, G14, C14, C21, C22, C23, C58

Suggested Citation

Rasekhschaffe, Keywan and Jones, Robert, Machine Learning for Stock Selection (February 8, 2019). Financial Analysts Journal, vol. 75, no. 3 (Third Quarter 2019), Available at SSRN: https://ssrn.com/abstract=3330946

Keywan Rasekhschaffe (Contact Author)

Gresham Investment Management, LLC ( email )

257 Park Avenue South
New York, NY 10010
United States

Robert Jones

Arwen Advisors ( email )

211 Warren Street
Newark, NJ 07103
United States

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
8,194
Abstract Views
19,440
Rank
1,474
PlumX Metrics