A Machine Learning Approach for Personalized Elective Recommendation in Engineering Education

In modern engineering education, students often struggle to select suitable open electives and core courses that align with their academic performance, personal interests, and long-term career goals. To address this issue, we present a hybrid recommendation framework grounded in machine learning, designed to aid academic curriculum planning in engineering institutions. The proposed system integrates both content and collaborative based filtering approaches, effectively utilizing student academic records, stated preferences, and detailed course metadata. Content-based filtering enables the system to analyze individual learner attributes and course features, while collaborative filtering predicts course ratings. This dual strategy enhances the accuracy and personalization of course recommendations. Experimental evaluations on real-world academic datasets demonstrated that the proposed system significantly improves elective selection accuracy and student engagement. This framework can serve as a valuable decision-support tool for both students and academic advisors, ultimately facilitating more informed curriculum planning and improved academic outcomes.