Predicting Corporate Bond Illiquidity via Machine Learning

61 Pages Posted: 26 Jun 2023 Last revised: 11 Dec 2023

See all articles by Axel Cabrol

Axel Cabrol

TOBAM

Wolfgang Drobetz

University of Hamburg

Tizian Otto

University of Hamburg

Tatjana Xenia Puhan

University of Mannheim - Department of International Finance

Date Written: December 7, 2023

Abstract

This paper tests the predictive performance of machine learning methods in estimating the illiquid-ity of U.S. corporate bonds. Machine learning techniques outperform the historical illiquidity-based approach, the most commonly applied benchmark in practice, from both a statistical and an economic perspective. Tree-based models and neural networks outperform linear regressions, which incorporate the same set of covariates. Gradient boosted regression trees perform particularly well. Historical illiquidity is the most important single predictor variable, but several fundametal and return- as well as risk-based covariates also possess predictive power. Capturing interactions and nonlinear effects among these predictors further enhances predictive performance.

Keywords: Illiquidity estimation, machine learning, corporate bonds

JEL Classification: G11, G12, C58, G17

Suggested Citation

Cabrol, Axel and Drobetz, Wolfgang and Otto, Tizian and Puhan, Tatjana Xenia, Predicting Corporate Bond Illiquidity via Machine Learning (December 7, 2023). Available at SSRN: https://ssrn.com/abstract=4489504 or http://dx.doi.org/10.2139/ssrn.4489504

Axel Cabrol

TOBAM

Wolfgang Drobetz

University of Hamburg ( email )

Moorweidenstrasse 18
Hamburg, 20148
Germany

Tizian Otto (Contact Author)

University of Hamburg ( email )

Moorweidenstraße 18
Hamburg, 20148
Germany

Tatjana Xenia Puhan

University of Mannheim - Department of International Finance ( email )

L9, 1-2
Mannheim, 68131
Germany

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
215
Abstract Views
593
Rank
255,283
PlumX Metrics