Towards developing hybrid educational data mining model (HEDM) for efficient and accurate student performance evaluation

Abstract

Many educational institutions use data mining for maintaining the student records, specifically academic performances, which are more significant. The academic performances of the students are to be analyzed for improving their results and also the overall results of the institutions. Moreover, the prediction of academic performance of students has been an important and developing research domain in educational data mining (EDM), in which data mining and machine learning techniques are used for deriving data from educational warehouse. With that, this paper develops a novel approach called hybrid educational data mining model (HEDM) for analyzing the student performance for effectively enhancing the educational quality for students. The proposed model evaluates the student performances based on distinctive factors that provide appropriate results. Furthermore, the model combines the efficiencies of Naive Baye’s classification technique and J48 Classifier for deriving the results and categorizing the student performance in precise manner. The model is evaluated with the benchmark education dataset that is available online in the WEKA environment. The results show that the proposed model outperforms the results of existing works in evaluating student performance in EDM.