Development of an Anti-Money Laundering System

In recent years, money laundering activities have shown rapid progress and has indeed become the main concern for governments and financial institutions all over the world. As per recent statistics, $800 billion to $2 trillion is the estimated value of money laundered annually. Accordingly, detecting and preventing illegal transactions becomes a serious challenge to the governments. To combat money laundering, especially in banking systems, effective techniques for detecting suspicious transactions must be developed. This project presents the development of an anti-money laundering system that leverages a hybrid approach by combining Artificial Neural Network (ANN) and Random Forest (RF) models or techniques. The system is built as an interactive web application, allowing users to insert new transactions with the existing accounts in the dataset and receive instant predictions on the potential of money laundering activities. It was observed that the hybrid technique achieved the highest f1-score of 93% with promising findings in decreasing the false positives as compared to the individual techniques. This indicates the model's potential as a powerful tool in the ongoing fight against money laundering. The results of this study could have significant implications for the financial sector, corporations, and governments, contributing to safer and more secure financial transactions.