Bond Risk Premia with Machine Learning

96 Pages Posted: 15 Jun 2019 Last revised: 23 Jun 2019

See all articles by Daniele Bianchi

Daniele Bianchi

School of Economics and Finance, Queen Mary University of London

Matthias Büchner

University of Warwick - Finance Group

Andrea Tamoni

Rutgers, The State University of New Jersey - Rutgers Business School at Newark & New Brunswick; London School of Economics & Political Science (LSE)

Multiple version iconThere are 2 versions of this paper

Date Written: April 1, 2019

Abstract

We compare a variety of machine learning methods for bond return predictability in the context of regression-based forecasting. Neural networks outperform both linear penalized regressions and non-linear shallow learners like random forests. These results hold both for annual and monthly holding-period bond excess returns. A novel approach based on ensembled deep neural networks shows that macroeconomic information substantially improves the out-of-sample predictability of bond excess returns. Non-linear features within, rather than across, economic categories are key to our results. Finally, using a simple trading strategy we show that the statistical performance of neural networks translates into large economic gains.

Keywords: Machine Learning, Ensembled Networks, Forecasting, Bond Return Predictability, Empirical Asset Pricing.

JEL Classification: C38, C45, C53, E43, G12, G17

Suggested Citation

Bianchi, Daniele and Büchner, Matthias and Tamoni, Andrea, Bond Risk Premia with Machine Learning (April 1, 2019). USC-INET Research Paper No. 19-11, April 2019. Available at SSRN: https://ssrn.com/abstract=3400941 or http://dx.doi.org/10.2139/ssrn.3400941

Daniele Bianchi (Contact Author)

School of Economics and Finance, Queen Mary University of London ( email )

Mile End Rd
Mile End Road
London, London E1 4NS
United Kingdom

HOME PAGE: http://whitesphd.com

Matthias Büchner

University of Warwick - Finance Group ( email )

Gibbet Hill Rd
Coventry, CV4 7AL
Great Britain

HOME PAGE: http://mbuechner.com

Andrea Tamoni

Rutgers, The State University of New Jersey - Rutgers Business School at Newark & New Brunswick ( email )

1 Washington Park
Newark, NJ 07102
United States

London School of Economics & Political Science (LSE) ( email )

Houghton Street
London, WC2A 2AE
United Kingdom
02079557303 (Phone)

Register to save articles to
your library

Register

Paper statistics

Downloads
107
Abstract Views
406
rank
17,122
PlumX Metrics