Bond Risk Premiums with Machine Learning

• 成果类型: Article
• 署名作者: Bianchi, Daniele; Buchner, Matthias; Tamoni, Andrea
• 署名单位: University of London; Queen Mary University London; University of Warwick; Rutgers University System; Rutgers University New Brunswick
• 刊物名称: REVIEW OF FINANCIAL STUDIES
• ISSN/ISSBN: 0893-9454
• DOI: 10.1093/rfs/hhaa062
• 发表日期: 2021
• 页码: 1046
• 关键词: term structure models; time-series; predictability; combination; returns; rates; forecasts; networks; number; tests

摘要

We show that machine learning methods, in particular, extreme trees and neural networks (NNs), provide strong statistical evidence in favor of bond return predictability. NN forecasts based on macroeconomic and yield information translate into economic gains that are larger than those obtained using yields alone. Interestingly, the nature of unspanned factors changes along the yield curve: stock- and labor-market-related variables are more relevant for shortterm maturities, whereas output and income variables matter more for longer maturities. Finally, NN forecasts correlate with proxies for time-varying risk aversion and uncertainty, lending support to models featuring both channels.