A Method for Evaluating the Interpretability of Machine Learning Models in Predicting Bond Default Risk Based on LIME and SHAP

TL;DR

This paper introduces a novel approach to evaluate the inherent interpretability of machine learning models in bond default prediction, using LIME and SHAP to assess model transparency beyond post-hoc analysis.

Contribution

It proposes a new method for assessing model interpretability directly, validated through bond default prediction models using LIME and SHAP.

Findings

Classification performance of algorithms evaluated

LIME and SHAP used to assess feature contributions

Interpretability assessments align with expectations

Abstract

Interpretability analysis methods for artificial intelligence models, such as LIME and SHAP, are widely used, though they primarily serve as post-model for analyzing model outputs. While it is commonly believed that the transparency and interpretability of AI models diminish as their complexity increases, currently there is no standardized method for assessing the inherent interpretability of the models themselves. This paper uses bond market default prediction as a case study, applying commonly used machine learning algorithms within AI models. First, the classification performance of these algorithms in default prediction is evaluated. Then, leveraging LIME and SHAP to assess the contribution of sample features to prediction outcomes, the paper proposes a novel method for evaluating the interpretability of the models themselves. The results of this analysis are consistent with the intuitive understanding and logical expectations regarding the interpretability of these models.