Educational Data Mining (EDM) promises better understanding of student behavior and knowledge, as well as new information on the implicit factors that contribute to student actions. This knowledge can be useful in guiding at-risk students, identifying priority learning needs for different groups of students, increasing graduation rates, making informed decisions about pedagogy, identifying student behavior and learning patterns, and optimizing student success. This study provides an overview of the body of knowledge regarding Educational Data Mining and its application in teaching and learning. In this paper the researcher highlight significant aspects of Big Data, including the Big Data technologies and the recent applications of Big Data in education. Finally, we explore and report on the challenges and difficulties encountered in EDM and present a discussion of future directions for the education and research community.

DOI: 10.1109/CSCI.2017.360

G. Javidi, L. Rajabion and E. Sheybani, "Educational Data Mining and Learning Analytics: Overview of Benefits and Challenges," 2017 International Conference on Computational Science and Computational Intelligence (CSCI), 2017, pp. 1102-1107, doi: 10.1109/CSCI.2017.360.