Bruno Deprez Toon Vanderschueren Bart Baesens Tim Verdonck Wouter Verbeke

Abstract

Money laundering presents a pervasive challenge, burdening society by financing illegal activities. The use of network information is increasingly being explored to more effectively combat money laundering, given it involves connected parties. This led to a surge in research on network analytics (NA) for anti-money laundering (AML). The literature on NA for AML is, however, fragmented and a comprehensive overview of existing work is missing. This results in limited understanding of the methods to apply and their comparative detection power. Therefore, this paper presents an extensive and unique literature review, based on 97 papers from Web of Science and Scopus, resulting in a taxonomy following a recently proposed fraud analytics framework. We conclude that most research relies on expert-based rules and manual features, while deep learning methods have been gaining traction. This paper also presents a comprehensive framework to evaluate and compare the performance of prominent NA methods in a standardized setup. We apply it on two publicly available data sets, comparing manual feature engineering, random walk-based, and deep learning methods. We conclude that (1) network analytics increases the predictive power, but caution is needed when applying GNNs based on the class imbalance and network topology, and that (2) care should be taken with open-source data as this can give overly optimistic results. The open-source implementation facilitates researchers and practitioners to extend upon the results and experiment on proprietary data, promoting a standardized approach for the analysis and evaluation of network analytics for AML.