Encoder–decoder graph neural network for credit card fraud detection

Credit card fraud is a significant problem, with millions of dollars lost each year. Detecting fraudulent transactions is a challenging task due to the large volume of data and the constantly evolving tactics of fraudsters. Likewise any detection problem, it is important to select relevant features that help distinguishing between fraudulent and non-fraudulent transactions. It is also crucial to design a model that effectively captures the relationships between involved entities such as merchants and customers. In this work, a prior stage of feature engineering is carried out. Then, the use of the Graph Neural Networks (GNNs) for credit card fraud detection is explored by leveraging the relationships between customers and merchants. We propose a novel encoder–decoder based GNNs that effectively captures the complex relationships and dependencies within credit card transaction data. The performance of the model is further improved by employing a graph converter for efficient graph data processing and batch normalization for reducing internal covariate shift and accelerating convergence. Our experiments on a large scale dataset delivered promising results that outperform other models in terms of precision, recall, and F1 score.