This study developed a model to classify attacks in a digital economy system using Random Forest and support vector machine. The Rational Unified process research methodology was used to develop the model. It was implemented using the spyder notebook development environment and using Python programming language version 3.7. In this research, experiments were conducted to check the performance of the models based on the accuracy, precision, recall rate, and F1 – Score. From the results achieved, the classification metrics shows that the Random Forest Classifier scored 98.9% in accuracy, precision, recall rate, and F1 – Score. The classification metrics show that the Support Vector Machine scored 98.9% in accuracy, precision, recall rate, and F1 – Score. The experimental result implies that Random Forest Classifier and Support Vector Machine Classifier scored the same in performance when compared. This research contributed to the enhancement of threat classification and made a proper decision(s) as to the rate of occurrence of specific types of threats using Random Forest and Support Vector Machine.