<![CDATA[The rapid development of information and communication technology has brought significant changes in various fields, including education. One of the technological innovations that has made a major contribution is machine learning. Education is an important aspect in human resource development. In this context, understanding the factors that influence student performance and classifying their learning outcomes is very important. This research aims to compare the best performance of two models, namely the C4.5 Algorithm and Naïve Bayes, then produce a decision tree to facilitate the classification of student performance. Using a student performance dataset totaling 2,392 data, this research classifies student performance from various aspects such as grades, class participation, learning skills, and contributions to extracurricular activities. In this research, the author performed data splitting with a ratio of 70:30 and 80:20, then evaluated the model with a confusion matrix and validated the model with 10-fold cross-validation. The best result of model testing was 85.82% using the C4.5 Algorithm with 10-fold cross-validation. The results of this research are expected to not only be able to classify student performance with good accuracy, but also provide valuable insights for educators and school and campus administrators to improve the overall quality of education.]]>
Copyrights © 2025
