用LIME和SHAP评估债券违约预测模型的内在可解释性
A Method for Evaluating the Interpretability of Machine Learning Models in Predicting Bond Default Risk Based on LIME and SHAP
- 结合LIME与SHAP分析特征对预测结果的贡献
- 验证了复杂模型可解释性随性能提升而下降的直觉
- 为金融风控模型提供可量化的可解释性评估方法
人工智能模型的可解释性分析方法（如LIME和SHAP）虽广泛应用，但多用于模型输出的后处理分析。尽管普遍认为模型越复杂，其透明度与可解释性越低，但目前尚无标准化方法评估模型本身的内在可解释性。本文以债券市场违约预测为案例，采用多种主流机器学习算法进行建模。首先评估各类算法在违约预测中的分类性能，随后利用LIME和SHAP分析样本特征对预测结果的贡献，提出一种评估模型自身可解释性的新方法。分析结果与人们对模型可解释性的直观认知及逻辑预期一致。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。