Abstract
Recommender engines is one of the popular information filtering tools that had been used by various layers of society. The concept of the recommender engines is to give the most relevant answer needed by the user. Book recommender is one of the popular implementations of recommender or filtering method. This is because there are so many books data in the world make it impossible for people to find one books without filtering. The aim of this project is to implement a of book recommender system, using some features from the collaborative filtering and content-based filtering. For this project, the user-item rating methods and the item-item rating had been implemented on the system to generate the list of recommendation books to the user. By using the root mean square error to evaluate the algorithm, the result obtained shows that collaborative filtering mean error value is less than the content-based filtering. This prove that the collaborative filtering is better at recommendation than content-based filtering, hi conclusion, this book recommender system can give a better recommendation of books by using the user-item technique.
Metadata
Download
55329.pdf
Download (120kB)