Hybrid content and collaborative filtering based recommendation system for e-learning platforms

Recommendation systems, although a well-studied topic, experience several shortcomings when applied on e-learning platforms. While collaborative filtering methods have enjoyed great success in making recommendations large scale e-commerce and social networking observation, users of platforms continually evolving preferences, which render weak. On the other end spectrum are content-based approaches. Although such more suited for platforms, primary concern is that these find it hard to generalize across content sources types. In this work, we present hybrid recommendation system combines desirable characteristics filtering, as well from task recommending course content/curriculum an system. Our easily incorporates changing user profiles (as learners step through content) also (courses taught by various departments) We apply our real dataset comprising 111 students organized into interdisciplinary groups. results showcase clear benefits enjoys, showing than 30 percentage points improvement over conventional techniques.