<![CDATA[College management requires graduation predictions to determine early prevention measures for drop out cases. The length of a student's study period can be caused by various factors, so it is necessary to know which students have the potential to graduate not on time. Data mining techniques can be used to explore new knowledge so that it can produce predictions of student graduation. Some algorithms that can be used are C4.5 and Naive Bayes. The purpose of this study was to predict the graduation of students from the Faculty of Social and Political Sciences at Andalas University using the C4.5 and Naive Bayes algorithms. The attributes used are age at college, gender, grade point average 1-4. The data used are FISIP undergraduate students who graduated in 2022 as many as 378. The results show that the accuracy of the Naive Bayes algorithm is better than C4.5 with the highest accuracy of 81.58%.]]>
Copyrights © 2023
