Timely graduation of students is essential for determining the quality of college. Universities must know the percentage of students' ability to complete their studies on time. So, to deal with this problem, data mining classification is carried out to predict student graduation on time to find patterns for student on-time graduation predictions. This research can yield new information to help colleges anticipate student graduations that are not on time. The method used is a classification data mining method with 4 algorithms: naïve Bayes, random forest, support vector machine (SVM), and artificial neural network (ANN). The attributes used are gender, parental income, length of guidance, working student status or not, semester 1 to semester 8 grades, and GPA. This study used Python 3 programming language on jupyter notebooks in Anaconda to process datasets. The distribution of datasets is divided by 70% for training data and 30% for testing data. The results of this study were obtained with the best algorithm accuracy in the support vector machine (SVM) algorithm is 0.94. Based on the results of this study, the accuracy is good for predicting student graduation on time.