A Matrix Factorization-based Collaborative Filtering Framework for Course Recommendations in Higher Education

Abstract

In higher education, students are often faced with a plethora of elective courses, making it challenging to determine which courses align with their academic and career goals. Recommender systems offer a potential solution to this problem by utilizing data on students' past academic performance, interests, and goals to provide personalized course recommendations. This paper proposes a personalized course recommendation system based on collaborative filtering with matrix factorization. The proposed method analyzes data from 603 students and provides third-year course recommendations for each student based on their individual preferences and past academic performance. The system has the potential to assist students in selecting the most appropriate elective courses, improving their academic performance, and enhancing their overall educational experience.