Can Machines Learn Capital Structure Dynamics?

69 Pages Posted: 22 Oct 2019 Last revised: 18 Mar 2023

See all articles by Shahram Amini

Shahram Amini

University of Denver

Ryan Elmore

University of Denver - Daniels College of Business

Özde Öztekin

Florida International University (FIU)

Jack Strauss

University of Denver - Daniels College of Business

Date Written: March 17, 2023

Abstract

Yes, they can! Machine learning models predict leverage better than linear models and identify a broader set of leverage determinants. They boost the out-of-sample R-squared from 36% to 56% over OLS and LASSO. The best performing model (random forests) selects market-to-book, industry median leverage, cash and equivalents, Z-Score, profitability, stock returns, and firm size as reliable predictors of market leverage. More precise target estimation yields a 10%-33% faster speed of adjustment and improves prediction of financing actions relative to linear models. Machine learning identifies uncertainty, cash flow, and macroeconomic considerations among primary drivers of leverage adjustments.

Keywords: Machine Learning, Target Leverage, Speed of Leverage Adjustment, Financing Actions

JEL Classification: G17, G30, G32, C10, C50

Suggested Citation

Amini, Shahram and Elmore, Ryan and Öztekin, Özde and Strauss, Jack, Can Machines Learn Capital Structure Dynamics? (March 17, 2023). Journal of Corporate Finance (JCF), Vol. 70, No. 1, pp. 1–22, October 2021, Available at SSRN: https://ssrn.com/abstract=3473322 or http://dx.doi.org/10.2139/ssrn.3473322

Shahram Amini (Contact Author)

University of Denver ( email )

2101 S. University Blvd
Denver, CO 80208
United States

HOME PAGE: http://https://daniels.du.edu/directory/shahram-amini/

Ryan Elmore

University of Denver - Daniels College of Business ( email )

2101 S. University Blvd.
Denver, CO 80208
United States

Özde Öztekin

Florida International University (FIU) ( email )

University Park
11200 SW 8th Street
Miami, FL 33199
United States

Jack Strauss

University of Denver - Daniels College of Business ( email )

2101 S. University Blvd.
Denver, CO 80208
United States

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

Paper statistics

Downloads
1,247
Abstract Views
3,544
Rank
30,649
PlumX Metrics