Machine Learning – Random Forests Predicts Cross Section of Corporate Bonds
Log in to collectAcademic paper
Predicting Individual Corporate Bond Returns
Xin He; Guanhao Feng; Junbo L. Wang; Chunchi Wu
- HKCity University of Hong Kong
- University of Science and Technology of China
- Hunan University
- ?City University of Hong Kong (CityU)
- ?University of Science and Technology of China (USTC)
- MOCity University of Macau
- City University of Seattle
- ?City University of Hong Kong (CityU) - Department of Economics and Finance
- ?Dept. of Economics and Finance, City Univ. of HK
- University at Buffalo, State University of New York
- Buffalo State University
- ?SUNY at Buffalo - School of Management
- ?The State University of New York (SUNY) at Buffalo - School of Management
Strategy in a nutshell
This strategy uses machine learning models, including random forests and lasso, to predict corporate bond returns across public and private bonds. By combining bond-specific characteristics with aggregate economic predictors, it forms long-short portfolios and market-timing strategies, achieving high out-of-sample forecast accuracy, strong Sharpe ratios, and significant alpha relative to benchmarks.
Economic rationale
The strategy works because corporate bonds exhibit predictable patterns that can be captured using extensive historical data, modern machine learning techniques, and comprehensive evaluation of both public and private bonds. This approach improves return forecasting and portfolio performance over traditional methods.