A method to improve the performance of predicting student exam results using machine learning techniques

Abstract

Predicting student performance to support and counsel at the right time is one of the most important problems that many researchers care about. Though many machine learning based methods have been proposed to identify at-risk students, the prediction results are still limited. In this paper, we suggest a method based on feature selection and over-sampling to improve the performance. The experimental results show that our approach is comparable to other methods.