Student academic performance is one of the important factors for student graduation. Therefore, many studies have been conducted in the field of education to identify factors that affect student performance. This research focuses on academic performance in online learning conditions by studying cases at XYZ university. Data were collected using Machine Learning techniques with the application of the Distributed Random Forest model, Naïve Bayes, Generalized Linear Model, and Gradient Boosting Machine algorithms. The results of this study indicate that the Distributed Random Forest and Gradient Boosting Machine models have an average accuracy of 99.83%. Researchers found variables that affect student learning performance, especially online learning, are final exam scores, midterm scores, attendance, assignment scores, amount of material given, number of assignments given, and number of clicks on material. From these findings, the researcher recommends that to improve the performance of the next learning, the implementation of learning should focus on improving the implementation of the Final Exams and the material on the learning platform
Copyrights © 2022