The recommender system is studied widely and applied in different domains in this era. However, the domain of course recommendation, particularly for elective courses, has yet to be thoroughly explored. Within the realm of student decision-making, the task of discerning the most fitting elective courses stands as a formidable challenge; however, in the context of this research, we tackle this predicament through the introduction of a collaborative filtering recommendation approach, which harnesses the information encapsulated within students’ prerequisite courses and the mean GPA of those prerequisites to furnish elective course recommendations predicated on the resemblances observed among prior students. The methodology employs the Singular Value Decomposition (SVD) algorithm to quantify the similarity between students and the elective courses’ recommendation procedure. The envisaged framework aims to reorient itself towards furnishing systematically precise and reasonable suggestions to students pursuing elective courses. We utilize real-world datasets to evaluate the proposed system and assess the model's performance using two popular evaluation matrices: root mean square error (RMSE) and mean absolute error (MAE). The proposed machine learning model experimental results demonstrate that the collaborative filtering recommendation system performs well. It offers students a precise forecast of the most appropriate Top-N elective courses, empowering them to discern a specific trajectory for their academic journey, facilitating informed decisions when selecting elective courses, and concurrently serving as a strategic means to attain a commendable outcome in their university pursuits. Furthermore, the proposed model contributes to the broader field of recommender systems by extending their application to the domain of course recommendation.