Applying Predictive Analytics in Elective Course Recommender System while preserving Student Course Preferences

In higher education scenarios, elective courses sought to provide a deeper insight of the trending advancements in the field of specialization for undergraduate students. So, choice of elective subjects during the pre-final or final year of the undergraduates play a crucial role as they help in shaping their career or area of specialization for future research. However, there exist numerous gaps and concerns that arise due to mismatch of the elective courses pre-requisites and the student’s possessed skills-set which result in degraded quality as well as student academic performance. This research study focuses on filling in these gaps by predicting the marks in different elective subjects for the current cohort of students, beforehand, as well as side by side preserving their explicit subject preferences. With the help of the proposed methodology an accuracy of 88% was achieved for providing efficient bilateral elective course recommendations.