用异构图神经网络捕捉信贷风险中的多方关联，提升预测效果。
Relational Graph Modeling for Credit Default Prediction: Heterogeneous GNNs and Hybrid Ensemble Learning
- 构建超大规模异构图，融合借款人属性与交易级实体数据
- 混合集成模型比纯GNN或树模型在AUC上提升显著
- 可解释性分析揭示关系信号对不同群体的影响差异
信贷违约风险源于借款人、金融机构及交易行为间的复杂交互。尽管强表格式模型在信用评分中仍具竞争力，但难以显式建模多表金融历史中的跨实体依赖。本文构建了一个包含超过3100万节点和5000多万边的超大规模异构图，整合了借款人属性与细粒度交易级实体（如分期付款、POS余额、信用卡记录）。我们评估了异构图神经网络（GNNs），包括异构GraphSAGE和关系感知注意力异构GNN，对比强表格式基线。结果表明，独立使用GNN仅带来有限性能提升，而将表格式特征与GNN生成的客户嵌入结合的混合集成模型表现最佳，显著提升了ROC-AUC和PR-AUC。此外，对比预训练能改善优化稳定性，但在通用图增强下下游收益有限。最后，通过结构化可解释性与公平性分析，揭示了关系信号如何影响子群体行为与筛选结果。
原文摘要 · Abstract (English)
Credit default risk arises from complex interactions among borrowers, financial institutions, and transaction-level behaviors. While strong tabular models remain highly competitive in credit scoring, they may fail to explicitly capture cross-entity dependencies embedded in multi-table financial histories. In this work, we construct a massive-scale heterogeneous graph containing over 31 million nodes and more than 50 million edges, integrating borrower attributes with granular transaction-level entities such as installment payments, POS cash balances, and credit card histories. We evaluate heterogeneous graph neural networks (GNNs), including heterogeneous GraphSAGE and a relation-aware attentive heterogeneous GNN, against strong tabular baselines. We find that standalone GNNs provide limited lift over a competitive gradient-boosted tree baseline, while a hybrid ensemble that augments tabular features with GNN-derived customer embeddings achieves the best overall performance, improving both ROC-AUC and PR-AUC. We further observe that contrastive pretraining can improve optimization stability but yields limited downstream gains under generic graph augmentations. Finally, we conduct structured explainability and fairness analyses to characterize how relational signals affect subgroup behavior and screening-oriented outcomes.
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。