Can machines learn capital structure dynamics? |
| |
| Institution: | 1. Daniels College of Business, Finance Department, University of Denver, United States;2. Daniels College of Business, Business Information and Analysis Department, University of Denver, United States;3. College of Business, Finance Department, Florida International University, United States;1. Carlson School of Management, University of Minnesota, Minneapolis, MN 55455, United States;2. School of Economics and Management, Tsinghua University, Weilun 317, Beijing, 100084, China;1. University of Maryland at College Park, College Park, United States of America;2. Department of Economics, University of Oklahoma, United States of America |
| |
| 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 R2 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: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
