The primary objective of this research is to monitor and detect fraudulent transactions within payment systems. As the use of smart transactions continues to increase, so does the prevalence of fraudsters. These individuals consistently seek to disrupt others by engaging in illegal activities, resulting in financial losses for customers while benefiting the fraudsters. Therefore, it is crucial to prioritize the monitoring and early detection of fraud. This article presents a unique Machine Learning (ML) model for the early identification of fraudulent transactions, utilizing a range-based classification approach. Many existing machine learning algorithms struggle to improve the misclassification rate while maintaining good accuracy. However, the proposed range-based classification model exhibits strong accuracy while addressing the issue of rising misclassification rates. The experimental results are presented through a bar graph and a classification report. Additionally, compare the proposed model with several existing technologies to showcase its effectiveness.