Neural Collaborative For Music Recommendation System

Abstract

In music there are various types of genres and every person has their own choice of the type of music they want to hear. Recommendation system is an important feature in an application, especially with the large number of choices for a particular item. With a good recommendation system, users will be helped by the suggestions given and can improve the user experience of the application. It is better provided by using collaborative filtering (CF) approach by recommending products related to one’s preferences history. However, CF approach still lacking in integrating complex users data. Therefore, hybrid technique could be the solution to polish the CF approach. Combining neural network and CF also called NCF thought to be better than CF alone. This study focuses on collaborative filtering approach combined with neural network or called neural collaborative filtering. In this study, we use 20,000 users, 6,000 songs, and 470,000 transaction ratings then predict the score using CF and NCF approach. The aim of this study is to differentiate recommendation systems with the use of CF alone and NCF. Through this research, it was found that NCF is better than user-based collaborative filtering in gather those playlist they really want to hear, but requires more time to build it.