Predicting individual corporate bond returns

IF 3.6 2区经济学 Q1 BUSINESS, FINANCE

Journal of Banking & Finance Pub Date : 2025-02-01 DOI:10.1016/j.jbankfin.2024.107372

Guanhao Feng , Xin He , Yanchu Wang , Chunchi Wu

引用次数: 0

Abstract

Using machine learning and many predictors, we find strong bond return predictability, with an out-of-sample R-squared of 4.48% and an annualized Sharpe ratio of 3.27. ML models identify important predictors for aggregate predictors (bond market returns, TERM and HML factors, GDP growth) and bond characteristics (downside risk, short-term reversal, return skewness, and credit spreads). Predictability varies over time, being stronger during periods of high investor risk aversion, slow economic growth, and strong cross-sectional factor explanatory power. Our results highlight the benefits of leveraging both cross-sectional and time-series predictors to forecast corporate bond returns while considering public and private bonds.

查看原文本刊更多论文

预测个别公司债券的回报

使用机器学习和许多预测因子，我们发现债券回报的可预测性很强，样本外r平方为4.48%，年化夏普比率为3.27。ML模型确定了总体预测因子（债券市场回报、期限和HML因素、GDP增长）和债券特征（下行风险、短期逆转、回报偏度和信用利差）的重要预测因子。可预测性随时间变化，在投资者风险厌恶程度高、经济增长缓慢和截面因素解释力强的时期表现得更强。我们的研究结果强调了在考虑公共债券和私人债券的同时，利用横截面和时间序列预测因子来预测公司债券回报的好处。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Banking & Finance Multiple-

CiteScore

6.40

自引率

5.40%

发文量

262

期刊介绍： The Journal of Banking and Finance (JBF) publishes theoretical and empirical research papers spanning all the major research fields in finance and banking. The aim of the Journal of Banking and Finance is to provide an outlet for the increasing flow of scholarly research concerning financial institutions and the money and capital markets within which they function. The Journal''s emphasis is on theoretical developments and their implementation, empirical, applied, and policy-oriented research in banking and other domestic and international financial institutions and markets. The Journal''s purpose is to improve communications between, and within, the academic and other research communities and policymakers and operational decision makers at financial institutions - private and public, national and international, and their regulators. The Journal is one of the largest Finance journals, with approximately 1500 new submissions per year, mainly in the following areas: Asset Management; Asset Pricing; Banking (Efficiency, Regulation, Risk Management, Solvency); Behavioural Finance; Capital Structure; Corporate Finance; Corporate Governance; Derivative Pricing and Hedging; Distribution Forecasting with Financial Applications; Entrepreneurial Finance; Empirical Finance; Financial Economics; Financial Markets (Alternative, Bonds, Currency, Commodity, Derivatives, Equity, Energy, Real Estate); FinTech; Fund Management; General Equilibrium Models; High-Frequency Trading; Intermediation; International Finance; Hedge Funds; Investments; Liquidity; Market Efficiency; Market Microstructure; Mergers and Acquisitions; Networks; Performance Analysis; Political Risk; Portfolio Optimization; Regulation of Financial Markets and Institutions; Risk Management and Analysis; Systemic Risk; Term Structure Models; Venture Capital.