Performance Prediction using Data Mining Techniques : A Study

Predicting student performance is important to make at university to prevent student failure. The drop-out number is one of the parameters that can be used to measure student performance and one important point that should be considered in the accreditation of a university. Data Mining is widely used to predict student performance, as well as data mining used in the field commonly referred to as Educational Data Mining. This study enabled Feature Selection to select high-quality attributes for student performance in the Department of Engineering in various universities. Subsequently, algorithms of two popular categories were used, the Bayesian Network and the Decision Tree, and they were compared to know the best predictive effect. The result revealed that the student attendance and GPA in the first semester were the highest in all Feature Selection methods, and the Bayesian Network is more successful than Decision Tree because it has a higher level of accuracy.