Detecting Fraud in Financial Networks: A Semi-Supervised GNN Approach with Granger-Causal Explanations

TL;DR

This paper introduces SAGE-FIN, a semi-supervised GNN method with Granger-causal explanations for detecting fraud in financial networks, effectively handling sparse labels and providing explainability for regulatory compliance.

Contribution

The paper presents a novel semi-supervised GNN approach with Granger causal explanations tailored for financial fraud detection, addressing label scarcity and explainability challenges.

Findings

SAGE-FIN outperforms baseline models on real-world financial network data.

It provides interpretable explanations for detected fraud using Granger causality.

The method requires no prior assumptions on network structure.

Abstract

Fraudulent activity in the financial industry costs billions annually. Detecting fraud, therefore, is an essential yet technically challenging task that requires carefully analyzing large volumes of data. While machine learning (ML) approaches seem like a viable solution, applying them successfully is not so easy due to two main challenges: (1) the sparsely labeled data, which makes the training of such approaches challenging (with inherent labeling costs), and (2) lack of explainability for the flagged items posed by the opacity of ML models, that is often required by business regulations. This article proposes SAGE-FIN, a semi-supervised graph neural network (GNN) based approach with Granger causal explanations for Financial Interaction Networks. SAGE-FIN learns to flag fraudulent items based on weakly labeled (or unlabelled) data points. To adhere to regulatory requirements, the flagged items are explained by highlighting related items in the network using Granger causality. We empirically validate the favorable performance of SAGE-FIN on a real-world dataset, Bipartite Edge-And-Node Attributed financial network (Elliptic++), with Granger-causal explanations for the identified fraudulent items without any prior assumption on the network structure.