Comparison of Tree-Based Machine Learning Algorithms to Predict Reporting Behavior of Electronic Billing Machines

Abstract

Tax fraud is a common problem for many tax administrations, costing billions of dollars. Different tax administrations have considered several options to optimize revenue; among them, there is the so-called electronic billing machine (EBM), which aims to monitor all business transactions and, as a result, boost value added tax (VAT) revenue and compliance. Most of the current research has focused on the impact of EBMs on VAT revenue collection and compliance rather than understanding how EBM reporting behavior influences future compliance. The essential contribution of this study is that it leverages both EBM’s historical reporting behavior and actual business characteristics to understand and predict the future reporting behavior of EBMs. Herein, tree-based machine learning algorithms such as decision trees, random forest, gradient boost, and XGBoost are utilized, tested, and compared for better performance. The results exhibit the robustness of the random forest model, among others, with an accuracy of 92.3%. This paper clearly presents our approach contribution with respect to existing approaches through well-defined research questions, analysis mechanisms, and constructive discussions. Once applied, we believe that our approach could ultimately help the tax-collecting agency conduct timely interventions on EBM compliance, which will help achieve the EBM objective of improving VAT compliance.