SmartBook: a hybrid filtering system for personalized book recommendation

The rapid growth of digital libraries and online bookstores has made it difficult for readers to discover books that match their interests. Traditional recommendation systems often rely only on collaborative filtering or content-based filtering, which limits recommendation accuracy and suffers from problems such as cold-start and data sparsity. This paper presents SmartBook, a hybrid book recommendation system that combines collaborative filtering and content-based filtering to generate personalized and relevant book suggestions. Collaborative filtering identifies users with similar reading preferences, while content-based filtering analyzes book attributes such as genre, author, language, publication year, and book description. A weighted hybrid approach is used to combine the scores obtained from both methods. The proposed system improves recommendation quality, increases personalization, and provides meaningful suggestions even for new users and newly added books. Experimental evaluation shows that the hybrid approach produces more accurate recommendations than individual recommendation techniques