Machine learning and network analysis for financial crime detection: Mapping and identifying illicit transaction patterns in global black money transactions

Abstract

The detection and prevention of malicious financial activities should be paramount for organizations in the US. Global economic integration, online banking, and increasing cases of cryptocurrency transactions have just increased the complexity of tracing illegal transactions. This research project examines the combined application and deployment of machine learning and network analysis in detecting black money transactions in the USA and globally. Machine learning and network analysis have emerged as a powerful mechanism in the fight against financial crime. Machine learning techniques, whereby systems learn through supervised and unsupervised learning, differ in that they can recognize patterns of financial data indicative of potentially fraudulent behavior. On the other hand, network analysis is one of the unique methods of detecting financial crimes, which derives power from presented relationships and interactions between sets of entities constituting transactional networks, such as people, companies, and accounts. This study used the Global Black Money Transactions dataset which revolved around financial transaction records involving unreported or illicit money, frequently for evading taxes, laundering money, or conducting illegal activities. Data come from financial institutions, government surveillance, whistleblowers, or investigations by the concerned law enforcement agencies. Rigorous data preprocessing steps were performed for the machine learning pipeline. In the current research project experiment, three machine learning algorithms were used: Logistic Regression, Random Forest, and XG-Boost. The performance indicators involved a set of standard metrics, including accuracy, precision, recall, F1 score, and AUC, which stands for Area Under the Curve. Despite lower accuracy, the XG-Boost algorithm was the best-performing algorithm. In terms of Precision, it correctly detected and predicted crimes, while the other models failed. Concerning the F1 Score, XG-Boost had the highest F1 score, balancing precision and recall. As per the AUC outcome, slightly better than Random Forest, XG-Boost was more capable of distinguishing between crime and non-crime transactions.

Keywords: Black Money Transactions, Financial Crime, Machine Learning, Network Analysis, Mapping Illicit Transactions, XG-Boost, Random Forest, Logistic Regression