Predictive Model to Detect Suspicious Transactions to mitigate the money laundering risk in the Non Banking Finance Industry

Abstract

In this paper, the researchers have studied the money laundering risk in the non-banking finance industry (NBFI) due to high amount of non-compliance incidents reported by the Central Bank of Sri-Lanka (CBSL). This has led to cause threats to the financial system of the country and further companies under the supervision of CBSL are running the reputation risk and worst case will lose the license to operate as a licensed finance entity. Research has sought to address this matter with the objective of developing a predictive model to detect suspicious transactions. As a result, the researchers could detect the variables that influence the suspicious transactions. This research has developed the model using different five algorithms. The study was directed to develop a classification machine learning model. Except for one algorithm, all other algorithms provided an average of 95% accuracy. Random Forest stood out as it reported 100% Recall for the model. Since the model's prime objective is to detect suspicious transaction the model with the best accuracy and recall were selected, therefore Random Forest is the best predictive model that detect suspicious transactions.