Data mining approaches to predict final grade by overcoming class imbalance problem

Data mining approaches have been used in business purposes since its inception; however, at present it is used successfully in new and emerging areas like education systems. Government of Bangladesh emphasizes the need to improve the education system. In this research, we use data mining approaches to predict students' final outcome, i.e., final grade in a particular course by overcoming the problem of imbalanced dataset. We implement several re-sampling techniques to balance the dataset so that could get better performance. Re-sampling techniques include SMOTE (Synthetic Minority Over-sampling Technique), ROS (Random over Sampling), RUS (Random under Sampling). Experimental results show that re-sampling techniques enhance the performance of the classification models that are developed to predict students' final grade in a particular course.