PROJECT TITLE :

A Systematic Review on Educational Data Mining - 2017

ABSTRACT:

Presently, instructional institutions compile and store huge volumes of knowledge, like student enrolment and attendance records, along with their examination results. Mining such knowledge yields stimulating information that serves its handlers well. Rapid growth in educational information points to the actual fact that distilling large amounts of knowledge needs a more subtle set of algorithms. This issue led to the emergence of the sector of educational information mining (EDM). Ancient information mining algorithms can not be directly applied to educational issues, as they'll have a particular objective and operate. This implies that a preprocessing algorithm has to be enforced 1st and only then some specific information mining methods will be applied to the problems. One such preprocessing algorithm in EDM is clustering. Several studies on EDM have targeted on the appliance of numerous information mining algorithms to instructional attributes. So, this paper provides over 3 decades long (1983-2016) systematic literature review on clustering algorithm and its applicability and usefulness within the context of EDM. Future insights are printed primarily based on the literature reviewed, and avenues for any analysis are identified.