期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2015
卷号：6
期号：6
页码：5114-5117
出版社：TechScience Publications
摘要：Online readers require tools to help them cope with the enormous of content available on the world-Wide Web. Selections are made by readers in traditional media with the help of assistance. Recommender system based on web data mining is very useful, more exact and provides worldwide services to the user. Recommender systems analyze patterns of user interest in items or products to provide recommendations for items that will suit a user’s taste.This includes both implicit intervention in the form of editorial oversight and explicit aid in the form of recommendation services such as movie reviews and restaurant guides.Several opportunities are provided by the electronic medium to offer recommendation services, ones that adapt over time to trace their evolving interests.Both content-based and collaborative systems can provide such a examine, but individually they both face shortcomings. To improve the accuracy various techniques are used.Main proposal of the project is the Singular value decomposition and Naive bayes classification to increase the accuracy of movie rating recommendation system.
关键词：Recommender system; recommendation;stability;iterative smoothing;Singular value decomposition and;Naive bayes classification.
