xFraud: Explainable Fraud Transaction Detection on Heterogeneous Graphs

At online retail platforms, it is crucial to actively detect risks of fraudulent transactions to improve our customer experience, minimize loss, and prevent unauthorized chargebacks. Traditional rule-based methods and simple feature-based models are either inefficient or brittle and uninterpretable. The graph structure that exists among the heterogeneous typed entities of the transaction logs is informative and difficult to fake. To utilize the heterogeneous graph relationships and enrich the explainability, we present xFraud, an explainable Fraud transaction prediction system. xFraud is composed of a predictor which learns expressive representations for malicious transaction detection from the heterogeneous transaction graph via a self-attentive heterogeneous graph neural network, and an explainer that generates meaningful and human understandable explanations from graphs to facilitate further process in business unit. In our experiments with xFraud on two real transaction networks with up to ten millions transactions, we are able to achieve an area under a curve (AUC) score that outperforms baseline models and graph embedding methods. In addition, we show how the explainer could benefit the understanding towards model predictions and enhance model trustworthiness for real-world fraud transaction cases.