Session Aware Music Recommendation System with User-based and Item-based Collaborative Filtering Method

Abstract

Recommender systems have been proven to be valuable means for web online users to cope with the information overload and have become one of the most powerful and popular tools in electronic commerce. The recommendations provided are aimed at supporting their users in various decision making process, such as what items to buy. In M u s i c R e c o m m e n d a t i o n S y s t e m , we recommend items to users based on their interest. First we use collaborative filtering method to identify the i t e m s which are similar and similarity among users based on the users listening history. P r o p o s e d A l g o r i t h m recommend the items to new users based on the item clusters and user clusters formed. L a t e r we have taken timestamp of user logs also into consideration to form Sessions. Finally we have evaluated the performance of the proposed algorithm with sessions and with -out sessions . Our experiment show that the accuracy of recommendation system with sessions outperformed the conventional user-based & item-based collaborative filtering method.