<![CDATA[In order to prevent money laundering and terrorism financing, it is critical for banks to develop an effective mechanism to detect suspicious transactions. Nowadays, one of the most widely developed methods is machine learning. This article aims to discuss the best algorithm model in machine learning to detect possibilities for Suspicious Financial Transactions in XYZ Bank. The machine learning method used is supervised machine learning, with three models compared: Decision Tree, Gradient Boosting, and Random Forest. The tool used is The Konstanz Information Miner (KNIME). According to the findings of the study, the best model for detecting the possibility of SFT in bank XYZ is random forest with an accuracy rate of 99,98%. Based on this level of accuracy, this study reveals that a machine learning approach using historical company data makes a significant contribution to XYZ bank in detecting Suspicious Financial Transactions.]]>
Copyrights © 2023
