Hybrid Course Recommendation System Design for a Real-Time Student Automation Application

Recommender systems provide personalized suggestions by processing user and item information interactions. Personalized product recommendations make it easier for users to access products that interest them. Course recommendation systems, on the other hand, aim guide students fields of in which they can succeed. On e-learning sites, there are many courses from different fields. Also, select than studying. However, educational institutions must follow a curriculum. Since each institution has distinct constraints course selection, specific approach problem is required develop recommender system. Due restrictive nature problem, developing system considered challenging. Therefore, consult faculty member when selecting enrollment. In this study, hybrid proposed using student with collaborative filtering content-based models. The provides consistent explicit implicit data, without predefined association rules. algorithms use grades as rating values. utilize text-based about converting them into feature vectors natural language methods. combination phase system, only one models used ensembling It found suggested achieve outperforming results all evaluation metrics. show values rank-aware metrics Precision@N, AP@N, mAP@N, NDCG@N individual combinations. particular, Bayesian ranking, model performs better any algorithm practice.