Paper: arXiv 2403.06482

Authors: Daixin Wang, Zhiqiang Zhang, Yeyu Zhao, Kai Huang, Yulin Kang, Jun Zhou

Abstract

User financial default prediction plays a critical role in credit risk forecasting and management. It aims at predicting the probability that the user will fail to make the repayments in the future. Previous methods mainly extract a set of user individual features regarding his own profiles and behaviors and build a binary-classification model to make default predictions. However, these methods cannot get satisfied results, especially for users with limited information. Although recent efforts suggest that default prediction can be improved by social relations, they fail to capture the higher-order topology structure at the level of small subgraph patterns. In this paper, we fill in this gap by proposing a motif-preserving Graph Neural Network with curriculum learning (MotifGNN) to jointly learn the lower-order structures from the original graph and higherorder structures from multi-view motif-based graphs for financial default prediction. Specifically, to solve the problem of weak connectivity in motif-based graphs, we design the motif-based gating mechanism. It utilizes the information learned from the original graph with good connectivity to strengthen the learning of the higher-order structure. And considering that the motif patterns of different samples are highly unbalanced, we propose a curriculum learning mechanism on the whole learning process to more focus on the samples with uncommon motif distributions. Extensive experiments on one public dataset and two industrial datasets all demonstrate the effectiveness of our proposed method.

Complexity vs Empirical Score

  • Math Complexity: 6.5/10
  • Empirical Rigor: 7.5/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper introduces an innovative approach combining motif-preserving Graph Neural Networks with curriculum learning to tackle financial default prediction. It demonstrates strong empirical rigor through testing across both public and industrial datasets, alongside a solid mathematical formulation of higher-order graph structures.

Research Flowchart

  flowchart TD
    A[Goal: Predict Financial Default using Higher-Order Graph Structures] --> B[Input: Financial & Social Interaction Datasets]
    B --> C[Construct Original Graph & Multi-View Motif-Based Graphs]
    C --> D[Motif-Preserving GNN & Motif-Based Gating Mechanism]
    D --> E[Curriculum Learning focused on Uncommon Motif Distributions]
    E --> F[Outcomes: Outperforms Baselines in Default Prediction & Credit Risk Forecasting]