A Framework for Interpreting Machine Learning Models in Bond Default Risk Prediction Using LIME and SHAP
Risks · 28.01.2026 · 14 (2) · 23
DOI: 10.3390/risks14020023 ↗Kurz gefasst
Fachartikel in der Zeitschrift Risks, online erschienen am 28.01.2026. Verfasst von Yan Zhang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Office of Philosophy and Social Sciences.
Abstract (Originalsprache)
Interpretability analysis methods, such as LIME and SHAP, are widely employed to explain the predictions of artificial intelligence models; however, they primarily function as post hoc tools and do not directly quantify the intrinsic interpretability of the models. Although it is commonly assumed that model transparency decreases with increasing complexity, there is currently no standardized framework for evaluating interpretability as an inherent property of AI models. In this study, we examine the prediction of bond defaults using several widely used machine learning algorithms. The classification performance of each algorithm is first evaluated, followed by the application of LIME and SHAP to assess the influence of input features on model outputs. Based on these analyses, we propose a novel approach for quantifying intrinsic model interpretability. The results align with theoretical expectations and provide insights into the trade-off between model complexity and interpretability.
Förderung
- National Office of Philosophy and Social Sciences
Zitieren
APA
Zhang, Y., Chen, L., & Tian, Y. (2026). A Framework for Interpreting Machine Learning Models in Bond Default Risk Prediction Using LIME and SHAP. Risks, 14(2), 23. https://doi.org/10.3390/risks14020023
Vancouver
Zhang Y, Chen L, Tian Y. A Framework for Interpreting Machine Learning Models in Bond Default Risk Prediction Using LIME and SHAP. Risks. 2026;14(2):23. doi:10.3390/risks14020023
BibTeX
@article{Zhang2026,
author = {Zhang, Yan and Chen, Lin and Tian, Yixiang},
title = {A Framework for Interpreting Machine Learning Models in Bond Default Risk Prediction Using LIME and SHAP},
journal = {Risks},
year = {2026},
volume = {14},
number = {2},
pages = {23},
doi = {10.3390/risks14020023}
}
EUVIMED