Movie Recommender System by using Item-based Collaborative Filtering Algorithm

Abstract

Recommender system applies discovery technique to support online users find desired products and services, etc. Recommender system technologies are needed that people can quickly produce high quality recommendations, even for very large-scale problems. To address these issues, this system implements movie recommender system using item-based collaborative filtering method.This system calculates prediction values to show the recommending movies.Therefore, to prove these values are the best quality results of recommending movies system and to show most likely movies for active user, this system measures average absolute deviation between a predicted rating and the user’s actual rating of a movie using MAE. Then, user requests ratings to the movies and this system calculates item-item similarity over movies. After that, this system predicts and recommends movies to the active user again.