期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2017
卷号：5
期号：4
页码：7982
DOI：10.15680/IJIRCCE.2017.05040262
出版社：S&S Publications
摘要：There are many online shopping websites such as, Amazon, Filpcart, Snapdeal and others. Number ofonline buyers and traders are increasing day by day. Therefore effective business techniques are needed to handle thelarge amount of data generated daily. Recommendation systems filter the data and provide adequate information to theusers. Therefore recommendation systems are very useful in online shopping websites, e-commerce so that user canfind the desired item form many items on website. Here we have proposed recommendation system for books toimprove user experience on online book store and give user more accurate recommendation. The aim of the paper is toprovide faster and efficient recommendations. We are using Apache Spark to build the recommendation system.Apache spark have ALS library for matrix factorization method which is collaborative filtering method. Along withthis we are doing popularity estimation of every book and consider it while recommendation. Popularity estimation isused to solve cold start problem in recommendation system.
关键词：Collaborative filtering; apache spark; ALS; popularity estimation; Matrix factorization model
