[论文解读] On the combination of graph data for assessing thin-file borrowers' creditworthiness

Ricardo Muñoz, Cristián Bravo+2 more|arXiv (Cornell University)|Nov 26, 2021

Financial Distress and Bankruptcy Prediction参考文献 50被引用 23

一句话总结

本文提出一种混合框架，结合手工特征、图嵌入（Node2Vec）和图神经网络（GNNs），以提升对薄档案借款人（即信用记录极少或无记录的个人与企业）的信用评分。通过将多种图表示学习（GRL）方法的输出聚合至梯度提升分类器，该方法在个人与企业信用评分任务中均显著提升预测性能，其中GNNs与工程特征表现出强烈协同效应，而Node2Vec的贡献可忽略不计。

ABSTRACT

The thin-file borrowers are customers for whom a creditworthiness assessment is uncertain due to their lack of credit history; many researchers have used borrowers' relationships and interactions networks in the form of graphs as an alternative data source to address this. Incorporating network data is traditionally made by hand-crafted feature engineering, and lately, the graph neural network has emerged as an alternative, but it still does not improve over the traditional method's performance. Here we introduce a framework to improve credit scoring models by blending several Graph Representation Learning methods: feature engineering, graph embeddings, and graph neural networks. We stacked their outputs to produce a single score in this approach. We validated this framework using a unique multi-source dataset that characterizes the relationships and credit history for the entire population of a Latin American country, applying it to credit risk models, application, and behavior, targeting both individuals and companies. Our results show that the graph representation learning methods should be used as complements, and these should not be seen as self-sufficient methods as is currently done. In terms of AUC and KS, we enhance the statistical performance, outperforming traditional methods. In Corporate lending, where the gain is much higher, it confirms that evaluating an unbanked company cannot solely consider its features. The business ecosystem where these firms interact with their owners, suppliers, customers, and other companies provides novel knowledge that enables financial institutions to enhance their creditworthiness assessment. Our results let us know when and which group to use graph data and what effects on performance to expect. They also show the enormous value of graph data on the unbanked credit scoring problem, principally to help companies' banking.

研究动机与目标

• 解决薄档案借款人（即信用记录极少或无记录的个人与企业）的信用评分挑战。
• 通过结合多种技术，克服孤立图表示学习（GRL）方法的局限性。
• 利用多源、全国范围的网络与金融数据，提升个人与企业信用评分的预测性能。
• 识别社会网络数据在信用资质评估中何时何地提供最大价值。
• 利用可解释人工智能（SHAP）提供关于特征重要性与模型行为的可操作洞察。

提出的方法

• 提出一种统一的信息处理框架，整合三种GRL方法：手工特征、Node2Vec嵌入与图神经网络（GNNs）。
• 将每种GRL方法的预测结果聚合为单一输入向量，输入至梯度提升分类器（XGBoost）。
• 使用覆盖拉丁美洲某国全部人口的独特全国性数据集，包含金融交易、社交互动与企业关系。
• 在四种信用评分场景中应用该框架：个人与企业申请评分，以及行为评分。
• 采用SHAP值解释特征贡献与模型决策，揭示哪些网络特征驱动预测结果。
• 使用标准指标验证性能：ROC曲线下面积（AUC）与柯尔莫哥洛夫-斯米尔诺夫统计量（KS）。

实验结果

研究问题

• RQ1 与单独使用各图表示学习（GRL）技术相比，结合多种GRL技术是否能提升信用评分性能？
• RQ2 组合后的网络特征提供了哪些关于信用风险的洞察？它们如何增强决策能力？
• RQ3 在个人或企业信用评分场景中，社会网络数据在哪类场景下带来最大性能提升？
• RQ4 哪些类型的网络特征（如：中心节点网络、家庭关系、供应商网络）对信用资质最具预测力？
• RQ5 不同GRL方法（特征工程、Node2Vec、GNNs）在不同借款人类型与评分场景中的贡献如何变化？

主要发现

• 手工特征与GNNs的结合带来最高性能提升，AUC与KS指标显著优于基线模型。
• 在无银行账户申请人评分中，所提框架实现最大性能增益，凸显其对金融排斥群体的价值。
• 在企业贷款中，企业生态体系（包括所有者、供应商与客户）提供了超越企业自身属性的关键预测信号。
• BenchScore基线模型仍具重要参考价值，但其相对影响在结合网络特征后减弱，表明网络数据增强了而非取代了传统指标。
• Node2Vec嵌入对模型性能贡献可忽略，表明在此情境下其作为独立特征工程方法的效用有限。
• 在个人信用评分中，家庭网络特征（FamilyNet）比更广泛的社会网络（EOWNet）更具信息量，凸显亲属关系在个人信用评估中的相关性。