Comparative Assessment of Fraudulent Financial Transactions using the Machine Learning Algorithms Decision Tree, Logistic Regression, Naïve Bayes, K-Nearest Neighbor, and Random Forest

Today, fast-paced technology plays an important role in financial transactions, especially in payment-related digital habits. As fraud is a major concern in online payments, many machine-learning approaches have been proposed to detect and prevent fraudulent payment transactions. This study aimed to evaluate Decision Tree, Logistic Regression, Naïve Bayes, K-Nearest Neighbor, and Random Forest in detecting fraudulent payment transactions. The results show that Random Forest, K-Nearest Neighbor, Decision Tree, and Logistic regression achieved total accuracy rates exceeding 99%. However, such impressive results do not necessarily indicate satisfactory performance. The results highlight the need to detect fraudulent transactions and investigate specific improvements to effectively manage and minimize unexpected financial transaction fraud.