Abstract:
In this era, the number of choices is overwhelming. Recommender systems solve this problem by searching through large volume of dynamically generated information to provide users with personalized content and services. Recommender systems support users by allowing them to move beyond catalog searches. Therefore, the need to use efficient and accurate recommendation techniques within a system that will provide relevant and dependable recommendations for users cannot be over-emphasized [3].
Most of the recommender systems use either content-based or collaborative filtering approach. Hence, this research will discuss the implementation of hybrid content-based and collaborative filtering approaches for a book recommender system. Hybrid approaches should be implemented because if only content-based approach that is implemented, the system will not suggest item outside user’s profile, a problem that can be solved by implementing collaborative filtering approach. However, collaborative filtering itself also has disadvantages that can be prevented using content-based approach, such as cold start and sparsity [6].
The implementation of this research will be using obtained data (1000 books), framework to support the front-end and back-end of the application, and libraries to help the implementation of the approaches from mathematical equation to programming code. The result of this research will be a web-based application. User will be able to get the best
ii
experience and result of finding a book that will suit user preference the most and increase the interest of user to read another genre of books [4].
