Enhancing Money Laundering Detection Through Machine Learning

Abstract

Money laundering is a worldwide issue that jeopardizes the stability and integrity of financial institutions. Many countries have implemented anti-money laundering laws and regulations to combat this. The basics of money laundering and its influence on the financial system, as well as existing strategies for detecting and combating it, are covered in this chapter. K- nearest neighbors, random forest, naive bayes, deep neural networks, and evolution metrics are examples of machine learning techniques and algorithms used to identify suspicious transactions. Financial institutions and regulatory bodies can strengthen their ability to detect and prevent money laundering activities and help to protect the integrity of the financial system by utilizing a variety of measures. In this work, the authors have presented a deep comparative analysis among various machine learning algorithms that are used in money laundering detection.