Machine learning for anomaly detection in money services business outlets using data by geolocation

Abstract

Since 2017, licensed money services business (MSB) operators in Malaysia report transactional data to the Central Bank of Malaysia on a monthly basis. The data allow supervisors to conduct off-site monitoring on the MSB industry; however, due to the increasing size of data and large population of the operators, supervisors face resource challenges to timely identify higher risk patterns, especially at the outlet level of the MSB. The paper proposes a weakly-supervised machine learning approach to detect anomalies in the MSB outlets on a periodic basis by combining transactional data with outlet information, including geolocation-related data. The test results highlight the benefits of machine learning techniques in facilitating supervisors to focus their resources on MSB outlets with abnormal behaviours in a targeted location.