Prediction of Study Period and Information on Judiciary in Higher Education Using the C5.0 Algorithm

Data Mining is often used to find patterns with certain techniques. Many data mining has been exploited against academic data. In Data Mining, choosing the right method depends on the goal and the process. One method that is often used in data mining is a decision tree. The concept of a decision tree is to convert data into a decision tree. There are several algorithms in implementing decision trees, including the C5.0 algorithm. In previous studies, research has been carried out on the prediction of the study period, but only focused on one final label category, namely the study period. Although several studies have been carried out related to graduation predictions, the novelty of this study uses multi-label, namely the study period and the results of the graduation statement. The purpose of this study will focus on predicting the length of study and student graduation outcomes using the Decision tree method with the C5.0 Algorithm. After implementation, we tested the accuracy by dividing the test data and training data differently. The test is carried out using the r2 score. The accuracy results obtained are 73%, and suggestions for further research are to add leave attributes and organizational history which can be a factor in students not graduating on time.