Bottom-Up Leading Macroeconomic Indicators: An Application to Non-Financial Corporate Defaults Using Machine Learning

40 Pages Posted: 22 Oct 2019 Last revised: 20 Aug 2021

See all articles by Tyler Pike

Tyler Pike

Board of Governors of the Federal Reserve System

Horacio Sapriza

Federal Reserve Banks - Federal Reserve Bank of Richmond; Board of Governors of the Federal Reserve System

Tom Zimmermann

University of Cologne

Date Written: September, 2019

Abstract

This paper constructs a leading macroeconomic indicator from microeconomic data using recent machine learning techniques. Using tree-based methods, we estimate probabilities of default for publicly traded non-financial firms in the United States. We then use the cross-section of out-of-sample predicted default probabilities to construct a leading indicator of non-financial corporate health. The index predicts real economic outcomes such as GDP growth and employment up to eight quarters ahead. Impulse responses validate the interpretation of the index as a measure of financial stress.

JEL Classification: C53, E32, G33

Suggested Citation

Pike, Tyler and Sapriza, Horacio and Zimmermann, Tom, Bottom-Up Leading Macroeconomic Indicators: An Application to Non-Financial Corporate Defaults Using Machine Learning (September, 2019). FEDS Working Paper No. 2019-70, Available at SSRN: https://ssrn.com/abstract=3473056 or http://dx.doi.org/10.17016/FEDS.2019.070

Tyler Pike (Contact Author)

Board of Governors of the Federal Reserve System ( email )

20th Street and Constitution Avenue NW
Washington, DC 20551
United States

Horacio Sapriza

Federal Reserve Banks - Federal Reserve Bank of Richmond ( email )

Board of Governors of the Federal Reserve System ( email )

20th Street and Constitution Avenue NW
Washington, DC 20551
United States

Tom Zimmermann

University of Cologne ( email )

Albertus-Magnus-Platz
Cologne, 50923
Germany

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

Paper statistics

Downloads
144
Abstract Views
819
Rank
429,497
PlumX Metrics