Study of Educational Data Mining Approaches for Student Performance Analysis

Abstract

Education is a vital component in the development of any country. In the education sector, research has been rapidly increasing using data mining techniques. The increase of e-learning resources, instrumental educational software, the use of the Internet in education, and the establishment of state databases of student information have created large repositories of educational data. Accurate prediction of students’ progress and their potential at the beginning of the degree is crucial for recognizing weak students and preventing their dropout at early stages. Educational Data Mining (EDM) is the application of data mining techniques to this specific type of dataset that comes from educational environments to address important educational questions. EDM assists in selecting improved learning materials and learning activities, with the main focus line to discover the hidden facts and figures concerning the performance of the students. This research study aims to reinforce the students’ academic performance prediction model, for higher studies using the Naïve Bayes classification method which has proved as the top classifier in making estimations accurately as compared to other classifiers of data mining. Different parameters like internal marks and sessional marks have been chosen to conduct this task. Internal marks are comprised of class performance, assignment marks, attendance marks, and presentation marks. Sessional marks are the results of exams conducted by the class instructors. In this way, early prediction can resolve the problem by indicating the factors that will cause their failure in academia.