A Framework for Items Recommendation System Using Hybrid Approach

Recommender systems are used to recommend items to users on different platforms, such as online shopping and movie theatres. Various platforms have used different recommendation techniques, such as content-based and collaborative filtering approaches, to recommend items to the users. In most cases, these approaches face different problems such as cold start and insufficient available information for the content attributes. In this research, we propose a hybrid recommendation approach using feature combination to curb one of the problems that arise from the use of collaborative or content-based recommendation approaches, in this case, the cold start problem. We propose using a feature combination hybridization method, which will entail using feature ratings obtained by the use of the collaborative filtering approach to enhance the content-based recommendation of articles.