Prediction of Secondary Students Performance: A Case Study

This study was conducted to predict students’ academic performance in a Mathematic course based on a case study among Portuguese secondary schools. A classification model is developed to explore different data mining algorithms that well represent the case study, which include the Logistic Regression, Boosted Decision Tree, Decision Forest, and Support Vector Machine. The results showed that the best classification performance is achieved with Boosted Decision Trees that outperformed Random Forests through the boosting capability. It is hoped that the findings from this paper will suggest effective methods for performance prediction in order to improve the quality of education resources.