Loan default predictability with explainable machine learning

doi:10.1016/j.frl.2023.104867

Loan default predictability with explainable machine learning

2024-02-01

2

PRE

AI

DOI：10.1016/j.frl.2023.104867

Original

Original request for help

Save

Abstract

En 中文

This paper studies loan defaults with data disclosed by a lending institution. We comprehensively compare the prediction performance of nine commonly used machine learning models and find that the random forest model has an efficient and stable prediction ability. Then, we apply an explainable machine learning method, i.e., SHapley Additive exPlanations (SHAP), to analyze the important factors affecting loan defaults. Moreover, we conduct an empirical study and find that the significant influencing factors are clearly consistent with those suggested by SHAP: the older the lender and the longer their working experience, the lower the risk of loan default.

Keywords:

Loan default

Machine learning

SHapley additive exPlanations

Loan default predictability with explainable machine learning

Abstract

Journal

Organization