A Personalized Recommendation System using Memory-Based Collaborative Filtering Algorithm

摘要

In recent years, with the exponential increase in Web usage, Recommendation Systems are being popularly used by various E-commerce sites to give remarkable recommendations to their users, such that the users as well as providers will get benefited. This paper presents a Personalized Recommendation System, which gives top most recommendations to both registered and unregistered users. The proposed Personalized Recommendation System is based on the most popular Collaborative Filtering (CF) technique, which uses the Item ratings available with the registered users' profile to provide recommendations. The performance of the proposed system is 10-fold cross validated on benchmark BookLens and MovieLens datasets of GroupLens Repository.