The Role of Machine Learning Approaches in the Anti Money Laundering Risk Assessment: A Systematic Literature Review

Mojtaba Alinaghi¹ Mohammad Fathian²

1) Master of Technology Management, Faculty of Progress Engineering, Iran University of Science and Technology, Tehran, Iran
2) Professor, Electronic Commerce, Faculty of Industrial Engineering, Iran University of Science and Technology, Tehran, Iran

IOI Code : XDEE-FAHHE
Publication : 17th international Management Conference(17imc.ir)
Abstract :
    With adopting a risk-based approach for performing anti-money laundering programs, banks consistently concern about recognizing high risk cases and assign financial and human resources for analyzing them optimally. In this study for identifying and prioritizing effective factors to assess money laundering risk, previous studies have been analyzed, then relevant information have been identified, extracted and classified. Nine papers were selected from 549 studies retrieved based on predefined inclusion and exclusion criteria. The findings of this review showed that, in the most studies that adopted machine learning for assessing money laundering risks, supervised algorithms namely Decision Trees attracted greater attention from researchers. Regarding the evaluation of models, criteria such as Accuracy and Precision has been adopted. Future work recommends expanding the scope of this review by including manual searches through snowball techniques in the references of the studies selected in this review, as well as in relevant journals and conferences.

Keywords : risk assessment money laundering machine learning literature review