用拓扑方法构建银行关联图，提升信用评级预测准确率
Prediction of Bank Credit Ratings using Heterogeneous Topological Graph Neural Networks
- 结合借贷网络与拓扑结构生成异构图
- 在真实全球数据集上预测准确率显著提升
- 适合金融风控与监管机构参考应用
标准普尔、穆迪等机构提供的银行信用评级影响经济稳定与利益相关方决策。准确及时的预测有助于支持决策、监管行动和投资者保护。然而，由于隐私问题，完整的银行间连接图常不可得，限制了图神经网络（GNN）的直接应用。本研究利用持久同调（persistent homology）构建捕捉银行间关系的网络，并将其与传统贷款网络融合，形成包含多源信息的异构网络，显著提升评级预测性能。在真实全球数据集上的实验验证了HTGNN的有效性。该研究对投资者和监管机构具有意义，有助于主动风险防控与市场干预策略制定。代码见：https://github.com/Liu-Jun-Yi/HTGNN。
原文摘要 · Abstract (English)
Agencies such as Standard & Poor's and Moody's provide bank credit ratings that influence economic stability and decision-making by stakeholders. Accurate and timely predictions support informed decision-making, regulatory actions, and investor protection. However, a complete interbank connection graph is often unavailable due to privacy concerns, complicating the direct application of Graph Neural Networks (GNNs) for rating prediction. our research utilizes persistent homology to construct a network that captures relationships among banks and combines this with a traditional lending network to create a heterogeneous network that integrates information from both sources, leading to improved predictions. Experiments on a global, real-world dataset validate the effectiveness of HTGNN. This research has implications for investors and regulatory bodies in enhancing proactive risk mitigation and the implementation of effective market interventions.The code can be find at https://github.com/Liu-Jun-Yi/HTGNN.
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。