xFraud: Explainable Fraud Transaction Detection

Download PDF

Abstract

At online retail platforms, it is crucial to actively detect the risks of fraudulent transactions to improve customer experience and minimize financial loss. In this work, we propose xFraud, an explainable fraud transaction prediction framework which is mainly composed of a detector and an explainer. The xFraud detector can effectively and efficiently predict the legitimacy of incoming transactions. Specifically, it utilizes a heterogeneous graph neural network to learn expressive representations from the informative heterogeneously typed entities of the transaction logs. The explainer in xFraud can generate meaningful and human-understandable explanations from graphs to facilitate further process in the business unit. In our experiments with xFraud on real transaction networks with up to 3.7 billion edges, xFraud is able to outperform various baseline models in many evaluation metrics while remaining scalable in the distributed setting. In addition, we show that the explainer can generate effective explanations to significantly assist the business analysis via both quantitative and qualitative evaluations.