A Comparative Study of Student Performance Prediction using Pre-Course Data

Students at Saudi universities face difficulty registering for the right course since Student performance there is no support offered to students that uniquely consider each situation. Machine learning techniques could be applied fill this gap by predicting grades of new courses student based on their historical data. This paper experiments with nine different prediction algorithms predict public university students. The data-set includes 215 and 180 various courses. models utilize obtained in semesters between 2015 2018 academic years evaluated 2019 year. Our result shows K-nearest neighbor ZScore model outperforms remaining respect Percentage Tick Accuracy (PTA), which difference two consecutive letter predicted grade observed grade. work achieved an 84% accuracy score PTA2, where actual less than or equal grades.