Framework of Recommendation Systems for Educational Data Mining (EDM) Methods: CBR-RS with KNN Implementation

The introduction of Educational Data Mining methods presents a prospect for educational management decision-makers in Educational Institutions to improve on the accuracy of predicting student academic performance. However, the diversity cum complexity of different educational data mining techniques poses a huge challenge resulting in uncertainty in making an educational management decision. The velocity and volume of educational data mining techniques make the challenge intractable. The Recommender System (RS) approach addresses the need for a decision support system to guide the process of appropriate Educational Data Mining (EDM) technique. The proposed JCOLIBRI framework is used in building Case-Based Reasoning—Recommender System (CBR-RS), which allows an interface for a non-expert user to define a query based on the problem domain. Furthermore, the research presents a framework of recommender systems through systematic review of different approaches of RS and EDM techniques in which non-expert user can find useful. Additionally, the research discusses how knowledge-based RS employs CBR-RS to overcome challenges such as cold-start, scalability, sparseness, grey sheep, contend limitations, overspecialization, and inflexible information. The CBR-RS was assessed using F1 metrics to quantify the quality of KNN algorithm used. The prototyped CBR-RS improves the performance of similarity-retrieval accuracy to 90%.