Tailored Elective Recommendations Using Collaborative Filtering and ML

An increase in the flexibility of curricula makes course electives a problem for the students, who cannot choose electives on their educational objectives and professional ambitions. The problem requires developing a hybrid recommendation system that integrates collaboration filtering, content-based approaches, and multi-criteria optimization to personalize electives recommendations. This system will draw from methodologies of recent studies in course recommendation systems and work around the problem of “cold start” with adaptive recommendations based on changing student interests and performances​. The system will first train on historical data, utilize multi-attribute criteria including some academic background, career objectives, and peer feedback, and incorporates genetic optimization to refine suggestions​. Results from empirical testing show the hybrid approach outperformed the single-method recommenders by precision and user satisfaction. the effectiveness in integrating machine learning and hybrid models into enhancing a student’s decision-making of the elective courses is demonstrated in this paper.