The Application of Data Mining for Predicting Academic Performance Using K-means Clustering and Naïve Bayes Classification

Data Mining is a multidisciplinary analyzing process that concentrating to extract and discover useful knowledge from data and information. The field of high education managements is giving a big concern to the knowledge discovery in the academic performance among different courses. Therefore, The education quality is judged by the level of the student’s success besides which accreditation that the educational institution can preserve its students. This is for the reason that, there are several factors affecting the academic performance and then the quality of education. The Naïve Bayes classifier is perhaps the most broadly applied probabilistic classifier approaches that can be used for the data exploration. This paper is using the Naïve Bayes classifier for educational data mining process to help in enhancing the quality distinction of the instructive system in higher education. This is by mining student evaluation data related to the instructor’s performance to study the main attributes that may affect the educational performance in different courses. Therefore, this paper is using k-means clustering algorithm, which is used to decide the ideal cluster center, so it can be the cluster centroid. Furthermore, the Naïve Bayes algorithm of classification process is applied for the academic evaluation data to generate rules which are studied and evaluated to predict the educational performance. The proposed system helps identifying the dropouts and provides the appropriate advising or counseling for educational management in performing knowledgeable decisions for considering and restructuring the educational curricula. Also, to enhance the academic experience of instructors that would ultimately improve the quality of educational environment of an educational institution.