A Scalable Product Recommendations Using Collaborative Filtering in Hadoop for Bigdata. (2016)

• Record Type: Journal Article
• Authors: Riyaz, P.A.; Varghese, Surekha Mariam
• Is Part Of: Procedia technology. Volume 24(2016)
• Page Start: 1393
• Page End: 1399
• Publication Date: 2016
• Subjects: Bigdata -- Recommendations -- Product -- Hadoop -- MapReduce -- HBase -- Collaborative ;; Technology -- Congresses; Technology -- Periodicals; Engineering -- Congresses; Engineering -- Periodicals; Engineering; Technology; Conference proceedings; Periodicals; 605
• DOI: 10.1016/j.protcy.2016.05.159
• Languages: English
• ISSNs: 2212-0173

Abstract

Abstract: The growth of data and information causes the need of next-generation databases and data science tools. Most of the business needs a service recommendation system which have been used by millions of users. Day by day, the amount of customers, products and information has grown rapidly, yielding the big data analysis problem for service recommender systems. Consequently, conventional recommender service systems often suffer from lack of scalability and efficiency problems when processing or analysis of this data on a large scale. To avoid these problems, a novel recommendations system using collaborative filtering algorithm is implemented in Apache Hadoop leveraging MapReduce paradigm for Bigdata. Apache Hadoop is an open framework for Distributed processing systems can process large volumes of data. It can be used for offline processing and not suitable for low latency analytics. Port data onto the next generation databases like HBase and optimize the performance of it. For the product recommendations the Amazon dataset is used. Proposed Framework have significant improvement in performance compared to conventional tools.