Predicting individual corporate bond returns

Guanhao Feng; Xin He; Yanchu Wang; Chunchi Wu

doi:10.1016/j.jbankfin.2024.107372

Predicting individual corporate bond returns

Guanhao Feng, Xin He^*, Yanchu Wang, Chunchi Wu

^*Corresponding author for this work

Department of Decision Analytics and Operations

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

8 Citations (Scopus)

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. © 2024 Elsevier B.V.

Original language	English
Article number	107372
Journal	Journal of Banking and Finance
Volume	171
Online published	13 Dec 2024
DOIs	https://doi.org/10.1016/j.jbankfin.2024.107372
Publication status	Published - Feb 2025

Bibliographical note

Full text of this publication does not contain sufficient affiliation information. Related Research Unit(s) information for this record is supplemented by the author(s) concerned.

Funding

Feng acknowledges financial support from the Hong Kong Research Grants Council (GRF11502721, GRF-11502023) and the Natural Science Foundation of China (NSFC-72203190). Feng is partially supported by the InnoHK initiative and the Laboratory for AI-Powered Financial Technologies. Wang acknowledges financial support from the Natural Science Foundation of China (72203138).

Research Keywords

Aggregate predictors
Bond characteristics
Forecast-implied investment gains
Machine learning
Time-varying return predictability

RGC Funding Information

RGC-funded

Access Output

10.1016/j.jbankfin.2024.107372

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{9617a26e77904d119a5f2b27b70ae65d,

title = "Predicting individual corporate bond returns",

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. {\textcopyright} 2024 Elsevier B.V.",

keywords = "Aggregate predictors, Bond characteristics, Forecast-implied investment gains, Machine learning, Time-varying return predictability",

author = "Guanhao Feng and Xin He and Yanchu Wang and Chunchi Wu",

note = "Full text of this publication does not contain sufficient affiliation information. Related Research Unit(s) information for this record is supplemented by the author(s) concerned.",

year = "2025",

month = feb,

doi = "10.1016/j.jbankfin.2024.107372",

language = "English",

volume = "171",

journal = "Journal of Banking and Finance",

issn = "0378-4266",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Predicting individual corporate bond returns

AU - Feng, Guanhao

AU - He, Xin

AU - Wang, Yanchu

AU - Wu, Chunchi

N1 - Full text of this publication does not contain sufficient affiliation information. Related Research Unit(s) information for this record is supplemented by the author(s) concerned.

PY - 2025/2

Y1 - 2025/2

N2 - 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. © 2024 Elsevier B.V.

AB - 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. © 2024 Elsevier B.V.

KW - Aggregate predictors

KW - Bond characteristics

KW - Forecast-implied investment gains

KW - Machine learning

KW - Time-varying return predictability

UR - http://www.scopus.com/inward/record.url?scp=85212865626&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85212865626&origin=recordpage

U2 - 10.1016/j.jbankfin.2024.107372

DO - 10.1016/j.jbankfin.2024.107372

M3 - RGC 21 - Publication in refereed journal

SN - 0378-4266

VL - 171

JO - Journal of Banking and Finance

JF - Journal of Banking and Finance

M1 - 107372

ER -

Predicting individual corporate bond returns

Abstract

Bibliographical note

Funding

Research Keywords

RGC Funding Information

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

GRF: Time-Varying Coefficient Modeling for Factor Selection in Asset Pricing

GRF: Textual Analysis of Corporate Bond Market

Cite this

Predicting individual corporate bond returns

Abstract

Bibliographical note

Funding

Research Keywords

RGC Funding Information

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

GRF: Time-Varying Coefficient Modeling for Factor Selection in Asset Pricing

GRF: Textual Analysis of Corporate Bond Market

Cite this