Student Academic Performance Prediction on Problem Based Learning Using Support Vector Machine and K-Nearest Neighbor

Abstract

Academic evaluation is an important process to know how well the learning process was conducted and also one of the decisive factors that can determine the quality of the higher education institution. Though it usually curative, the preventive effort is needed by predicting the performance of the student before the semester begin. This effort aimed to reduce the failure rate of the students in certain subjects and make it easier for the PBL tutor to create appropiate learning strategies before the tutorial class begin. The purpose of this work is to find the best data mining technique to predict student academic performance on PBL system between two data mining classification algorithms. This work applied and compared the performance of the classifier models built from Support Vector Machine (SVM) and K-Nearest Neighbor (KNN). After preprocessed the dataset, the classifier models were developed and validated. The result shows that both algorithms were giving good accuracy by 97% and 95,52% respectively though SVM showing the best performance compared to KNN in F-Measure with 80%. The further deployment is needed to integrate the model with academic information system, so that academic evaluation can be easily done.