Predicting Critical Courses Affecting Students Performance: A Case Study

Abstract

Predicting student academic performance is one of the important applications of educational data mining. It allows academic institutions to provide appropriate support for students facing difficulties. Classification is a data mining technique that can be used to build prediction models. In this paper, we use the ID3 decision tree induction algorithm to build prediction models for academic performance. Our models are built based on records for female students in the Bachelors program at the Information Technology (IT) department, King Saud University, Riyadh, Saudi Arabia. The results indicate that reliable predictions can be achieved based on the performance of students in second year courses. We also identify key courses that can be used as performance predictors. We believe our findings are useful for decision makers at the IT department.