A Method for Evaluating the Interpretability of Machine Learning Models in Predicting Bond Default Risk Based on LIME and SHAP
This work addresses the problem of evaluating model interpretability for researchers and practitioners in finance, but it is incremental as it builds on existing interpretability tools.
The paper tackled the lack of standardized methods for assessing the inherent interpretability of machine learning models, using bond default risk prediction as a case study, and proposed a novel evaluation method based on LIME and SHAP, with results aligning with intuitive expectations about model interpretability.
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.