A Course Recommendation System Based on Collaborative Filtering Algorithm

With the development of information technology and the spread of online education, people have gradually moved from an era of information scarcity to an era of information overload. In order to solve the problem of how match massive course resources with user needs. This study designs a course recommendation system based on collaborative filtering algorithm. We utilized nearly 200000 learning record data and over 40000 user data from the education platform, and constructed an item similarity matrix, personalized user recommendations were made based on the matrix. Subsequently, the user-based recommendation model, UserCF, and the object-based recommendation model, ItemCF, were proposed. We further proposed the multi process idea to optimize the training efficiency of the model. The experimental results showed that this method can efficiently and accurately recommend online courses on educational platforms, with the recall rate is 18%, with accuracy and coverage rates of21% and 73%, respectively. Our algorithm not only maintains a balance between accuracy and recall, but also has good coverage, achieving personalized recommendations for designated users.