<![CDATA[Good student academic performance is the key to success in the quality of education at university. One of the factors that influence academic success by utilising information technology and data analytics. This research incorporates GPA scores and other external factors that can affect students' academic performance such as parents’ job and latest education, address, gender, extracurricular, etc. This research uses Machine Learning; Decision Tree, Random Forest, K-Nearest Neighbour, Support Vector Classifier, Naive Bayes, and Gaussian as methods to analyse and predict the academic performance of students of the Information Systems Study Program, Faculty of Computer Science at the University of Jember. The results showed that the Decision Tree algorithm has the highest accuracy value of 0.9264 followed by Random Forest and K-Nearest Neighbour. Meanwhile, the prediction results show that the Decision Tree, K-nearest neighbour, and Random Forest algorithms can predict the same results]]>
Copyrights © 2024
