Financial Default Prediction via Motif-preserving Graph Neural Network with Curriculum Learning

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

Rating

1660
Battle Count: 116

Relevance

7/10
Highly relevant for credit risk assessment in financial services, but not directly applicable to trading strategies

Implementation Complexity

8/10
Requires implementation of custom GNN architecture and motif-based graph construction

Reproducibility

4/5
Experiments conducted on public and industrial datasets with implementation details provided

About this paper

Methodology: MotifGNN. Problem types: Classification, Financial Default Prediction.

The interactive Everscope explorer (charts, battles, favorites) loads below.