Academic Performance Prediction of At-Risk Students using Machine Learning Techniques

Imparting quality education is a top priority of higher education institutions. Leaving at risk students unattended would adversely impact the quality of education. Predicting the academic performance of students is one of the basis for improving the quality of education, as it would help the institution to take early and timely measures to support the low-performing students and improve their performance. At the same time, it has identified that the prediction of student performance considered as challenging one due to large dataset in educational environment. However, Educational Data Mining (EDM) using machine learning techniques is an emerging research area, which allows the researchers to effectively process and evaluate the educational data collected from different sources. In this paper, we propose the use of support vector machine (SVM) on an imbalanced dataset to predict the academic performance of students.