About this document
Graph Neural Network for Fraud Detection by manoj2m24 is a document available to read on EtoBox.
This dissertation by Sunidhi Jain explores a Graph Neural Network (GNN) framework for detecting healthcare fraud, addressing the limitations of traditional fraud detection methods. The study constructs a Patient-Provider-Claim graph and demonstrates that the HeteroFraudGNN model significantly outperforms conventional models, achieving an AUC-PR of 0.658 compared to 0.469 for Logistic Regression. The findings highlight the effectiveness of GNNs in uncovering complex fraud patterns through relational learning
- Author
- manoj2m24
- Language
- EN