Risk Assessment for Networked-guarantee Loans Using High-order Graph Attention Representation

Abstract

Assessing and predicting the default risk of networked-guarantee loans is critical for the commercial banks and financial regulatory authorities. The guarantee relationships between the loan companies are usually modeled as directed networks. Learning the informative low-dimensional representation of the networks is important for the default risk prediction of loan companies, even for the assessment of systematic financial risk level. In this paper, we propose a high-order graph attention representation method (HGAR) to learn the embedding of guarantee networks. Because this financial network is different from other complex networks, such as social, language, or citation networks, we set the binary roles of vertices and define high-order adjacent measures based on financial domain characteristics. We design objective functions in addition to a graph attention layer to capture the importance of nodes. We implement a productive learning strategy and prove that the complexity is near-linear with the number of edges, which could scale to large datasets. Extensive experiments demonstrate the superiority of our model over state-of-the-art method. We also evaluate the model in a real-world loan risk control system, and the results validate the effectiveness of our proposed approaches.

Risk assessment for contagion path in complex loan network

“…Meng 等 [24] 论证了企业所处节 点的 Kshell 散度和企业在担保网络中的违约率存在相关性. Cheng 等 [7] 进一步探索了使用网络表示 学习方法在个体企业风险评估中的作用, 表明了网络特征的重要性. 现有针对担保网络的信贷风险评 估主要针对网络中的个体节点进行预测, 本文从风险传播的传染路径的角度入手, 探索对担保网络的 系统性风险进行评估和分析, 为风险监控提供全局的数据和方法支撑.…”

“…综上, 总体风险评估网络的完整代价函数表示为 [29] 、长短时记忆 循环神经网络 (long short term memory, LSTM)、 快速图卷积神经网络 (simplifying graph convolutional networks, SGC) [30] 、图注意力机制模型 (graph attention network, GAT) [6] 和高阶图注意力网络 (highorder graph attention representation, HGAR) [7] . 其中对于个体风险评估的方法, 我们使用算术平均聚 合将其扩展至路径的风险评估任务中.…”

Spatio-Temporal Attention-Based Neural Network for Credit Card Fraud Detection

“…Attentional Convolution Neural Network Many recent works have shown the benefit of combining an attention mechanism in convolutional neural networks for a wide range of prediction tasks (Allamanis, Peng, and Sutton 2016;Vaswani et al 2017), such as depth estimation (Xu et al 2018), default prediction (Cheng et al 2019a) or language understanding (Shen et al 2018). For instance, pervasive attention are employed on 2D convolutional neural networks for sequence-to-sequence prediction (Elbayad, Besacier, and Verbeek 2018).…”

iConViz: Interactive Visual Exploration of the Default Contagion Risk of Networked-Guarantee Loans

“…Dan used force-directedgraph visualiza-tion to analyze Bitcoin transaction activity and explore dynamically generated patterns of algorithmic behavior [28]. We are the first to identify and report a visual analytic framework for the risk management problem with networked loans [30,10,9].…”

“…Zooming in, there is a significant directed subgraph microstructure. Some prime aspects may be familiar to loan assessment domain experts [30,9,10], but the collective financial properties of those microstructures are unclear and need to be explored.…”