Performance Evaluation of Popular Supervised Learning Algorithms Towards Cardiovascular Disease

Many studies have discussed the advantages of supervised learning for dealing with extensive data on heart disease. However, only a few studies evaluate the performance of supervised learning algorithms. This research builds a classification model using supervised learning algorithms, including C4.5, Random Forest, Logistic Regression, and Support Vector Machine. The data processed is in the form of category data with character data types. The accuracy, precision, and performance evaluation results show that the Logistic Regression Algorithm has the most superior value compared to the others. On the other hand, it was found that the C4.5 and SVM algorithms had anomalous events. Although the accuracy and precision values of C4.5 were superior to SVM, SVM had better performance.