Predicting Student Performance using Classification and Regression Trees Algorithm

Abstract

Now a days Internet and Web technologies providing students opportunities for flexible interactivity with study materials, peers and instructors. And also generating large amounts of usage data that can be processed and reveal behavioral patterns of study and learning. In this paper, to predict course performance we extracted data from a Moodle-based blended learning course and build a student model. Classification and Regression Trees (CART) decision tree algorithm was used to classify students and predict those at risk, based on the impact of four online activities: message exchanging, group wiki content creation, course files opening and online quiz taking. The correct classifications in results prove that the model is sensitive to categorize very specific groups at risk.