[论文解读] Enabling Machine Learning Algorithms for Credit Scoring -- Explainable Artificial Intelligence (XAI) methods for clear understanding complex predictive models

Przemysław Biecek, Marcin Chlebuś+6 more|arXiv (Cornell University)|Apr 14, 2021

Financial Distress and Bankruptcy Prediction被引用 6

一句话总结

本文表明，先进的树模型机器学习模型（如XGBoost和LightGBM）在保持通过可解释人工智能（XAI）技术实现可解释性的同时，其在信用评分中的准确性优于传统的逻辑回归模型。基于波兰大型信用局数据集，作者展示了SHAP和LIME等XAI方法使从业者能够理解并信任复杂模型，从而解决了金融风险管理中的‘黑箱’障碍。

ABSTRACT

Rapid development of advanced modelling techniques gives an opportunity to develop tools that are more and more accurate. However as usually, everything comes with a price and in this case, the price to pay is to loose interpretability of a model while gaining on its accuracy and precision. For managers to control and effectively manage credit risk and for regulators to be convinced with model quality the price to pay is too high. In this paper, we show how to take credit scoring analytics in to the next level, namely we present comparison of various predictive models (logistic regression, logistic regression with weight of evidence transformations and modern artificial intelligence algorithms) and show that advanced tree based models give best results in prediction of client default. What is even more important and valuable we also show how to boost advanced models using techniques which allow to interpret them and made them more accessible for credit risk practitioners, resolving the crucial obstacle in widespread deployment of more complex, 'black box' models like random forests, gradient boosted or extreme gradient boosted trees. All this will be shown on the large dataset obtained from the Polish Credit Bureau to which all the banks and most of the lending companies in the country do report the credit files. In this paper the data from lending companies were used. The paper then compares state of the art best practices in credit risk modelling with new advanced modern statistical tools boosted by the latest developments in the field of interpretability and explainability of artificial intelligence algorithms. We believe that this is a valuable contribution when it comes to presentation of different modelling tools but what is even more important it is showing which methods might be used to get insight and understanding of AI methods in credit risk context.

研究动机与目标

• 评估现代机器学习模型在信用评分中相较于传统逻辑回归的性能表现。
• 解决复杂‘黑箱’模型在金融风险管理中可解释性的挑战。
• 展示SHAP和LIME等XAI方法在解释树模型预测结果方面的实际应用价值。
• 为在真实世界信用风险环境中部署高精度、可解释模型提供框架。
• 弥合人工智能驱动的信用评分中模型性能与监管机构及从业者信任之间的差距。

提出的方法

• 本研究基于大规模波兰信用局数据集，对比了逻辑回归、经过WOE变换的逻辑回归以及先进的树模型（XGBoost、LightGBM）的性能表现。
• 应用SHAP（SHapley Additive exPlanations）和LIME（Local Interpretable Model-agnostic Explanations）等XAI技术，对复杂模型的预测结果进行解释。
• 采用标准信用风险指标（包括AUC-ROC、KS统计量和基尼系数）评估模型性能。
• 利用特征重要性分析与部分依赖图，分析模型行为及客户层面的风险驱动因素。
• 模型在匿名化的贷款机构数据上进行训练与验证，确保其具备现实世界的相关性。
• 可解释性框架的设计旨在支持监管合规与管理决策。

实验结果

研究问题

• RQ1 现代树模型机器学习模型在信用评分中能否显著提升预测准确性，超越传统的逻辑回归？
• RQ2 SHAP和LIME等XAI技术在多大程度上能够增强复杂‘黑箱’模型在信用风险应用中的可解释性？
• RQ3 XAI方法提供的特征重要性与局部解释如何支持风险管理和监管监督？
• RQ4 在金融机构中使用先进机器学习模型时，模型准确性与可解释性之间存在何种权衡？
• RQ5 XAI方法能否在不损害模型性能的前提下，有效集成到现有的信用风险工作流程中？

主要发现

• XGBoost和LightGBM模型取得了最高的AUC-ROC得分，显著优于逻辑回归和WOE变换模型。
• 表现最佳的树模型AUC-ROC超过0.75，展现出在违约预测中卓越的区分能力。
• 基于SHAP的解释表明，收入负债比与近期信用使用率是预测违约的最关键特征。
• LIME提供的局部可解释性使风险分析师能够以高精度评估单个客户的风险因素。
• XAI方法的集成降低了复杂模型的透明度盲区，显著提升了信用风险从业者对模型的信任度。
• 本研究证实，高精度模型在受监管的金融环境中既可解释，也可实际部署。