Gated Mixture Variational Autoencoders for Value Added Tax audit case selection

In this work, we address the problem of targeted Value Added Tax (VAT) audit case selection by means of machine learning. This is a challenging problem that has remained rather elusive for EU-based Tax Departments, due to the inadequate quantity of tax audits that can be used for conventional supervised model training. To this end, we devise a novel Gated Mixture Variational Autoencoder deep network, that can be effectively trained with data from a limited number of audited taxpayers, combined with a large corpus of filed VAT returns. This gives rise to a semi-supervised learning framework that leverages the latest advances in deep learning and robust regularization using variational inference. We developed our approach in collaboration with the Cyprus Tax Department and experimentally deployed it to facilitate its audit selection process; to this end, we used actual VAT data from Cyprus-based taxpayers. This way, we obtained strong empirical evidence that our approach can greatly facilitate the VAT audit case selection process. Specifically, we obtained up to 76% out-of-sample accuracy in detecting whether a significant tax yield will be generated from a specific prospective VAT audit.