Yield Spread Selection in Predicting Recession Probabilities: A Machine Learning Approach

20 Pages Posted: 27 Jan 2021 Last revised: 7 Jan 2022

See all articles by Jaehyuk Choi

Jaehyuk Choi

Peking University - HSBC School of Business

Desheng Ge

Peking University - HSBC School of Business

Kyu H. Kang

Korea University

Sungbin Sohn

Peking University - HSBC Business School

Date Written: January 1, 2021

Abstract

The literature on using yield curves to forecast recessions customarily uses 10-year--three-month Treasury yield spread without verification on the pair selection. This study investigates whether the predictive ability of spread can be improved by letting a machine learning algorithm identify the best maturity pair and coefficients. Our comprehensive analysis shows that, despite the likelihood gain, the machine learning approach does not significantly improve prediction, owing to the estimation error. This is robust to the forecasting horizon, control variable, sample period, and oversampling of the recession observations. Our finding supports the use of the 10-year--three-month spread.

Keywords: Yield curve, estimation risk, density forecasting, machine learning

JEL Classification: C52, E32, E43

Suggested Citation

Choi, Jaehyuk and Ge, Desheng and Kang, Kyu H. and Sohn, Sungbin, Yield Spread Selection in Predicting Recession Probabilities: A Machine Learning Approach (January 1, 2021). Available at SSRN: https://ssrn.com/abstract=3723717 or http://dx.doi.org/10.2139/ssrn.3723717

Jaehyuk Choi

Peking University - HSBC School of Business ( email )

University Town
Nanshan District
Shenzhen, Guang Dong 518055
China

HOME PAGE: http://jaehyukchoi.net/phbs_en

Desheng Ge

Peking University - HSBC School of Business ( email )

University Town
Nanshan District
Shenzhen, Guang Dong 518055
China

Kyu H. Kang (Contact Author)

Korea University ( email )

1 Anam-dong 5 ka
Seoul, 136-701

Sungbin Sohn

Peking University - HSBC Business School ( email )

University Town
Nanshan District
Shenzhen, Guang Dong 518055
China
+86-755-26035324 (Phone)
+86-755-26035344 (Fax)

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
62
Abstract Views
409
rank
447,188
PlumX Metrics