IJSART - Volume 3 Issue 4 –APRIL 2017 ISSN [ONLINE]: 2395-1052 Page | 1073 www.ijsart.com Personalized News Recommendation System Based on Consumers’ Click Behavior Aarti Gaikwad 1 , Geeta Narle 2 , Mohini Malge 3 , Namrata Mulay 4 , Noorjahan Sayyed 5 Department of Information Technology 1, 2, 3, 4, 5 D. Y. Patil College Of Engineering Akurdi, Pune Abstract-The development of the Internet, more and more people read news on the Internet. However, facing the massive data, consumers need to spend much time on choosing news they prefer. Therefore, providing an effective personalized news recommendation for consumers will promote consumer’s experience of browsing news greatly.The news browsing sequence of a consumer can be obtained from the consumer’s click behaviour on the Internet. Here, some potential associations between news using the news browsing sequence of a consumer will be found. Then, personalized news recommendation for different consumers can be provided according to these potential associations. In this paper, an improved personalized news recommendation algorithm based on consumers’ click behaviour is proposed. Through doing experiments on real news browsing data, the recommendation result is better and the new algorithm is proved to be feasible. Keywords-Recommendation , Browsing , Personalised, Consumers I. INTRODUCTION In this project we are going to create one web application which will show news in portal where users will come and will be using it.Behind the scene all user's behavior will be tracked by using logging mechanism(server logging). i.e. if user is clicking some news which he was not interested earlier,we will write some algorithm to conclude user's current interest Modules in this project . 1) Users module this will store user personilized profile which will in showing some recommended news on portal when he log in 2) Newzmodulethis module will have all information related to newz management(admin module can create different newz here). the newz will be related to each other by parent-child hierarchy 3) Analyzer module this module will be core module which is responsible for retrieving useeful & analyzed information from raw information.With the development of the Internet, more and more people read news on the Internet. However, facing the massive data, consumers need to spend much time on choosing newsthey prefer. Therefore, providing an effective personalized news recommendation for consumers will promote consumers’ experience of browsing news greatly. The research on the personalized recommendation system can be roughly divided into four kinds, namely recommendation based on content, recommendation based on collaborative filtering, recommendation based on knowledge and hybrid recommendation. The recommendation based on content is a method which is widely used in practice. This method finds the relation between different news according to the content. Then, the preference of consumers can be obtained and applied to news recommendation. As text processing technology gets more sophisticated, the research on the recommendation based on content is becoming more and more mature. The recommendation based on collaborative filtering is a method which is widely studied in recommendation system.This method has two branches, namely collaborative filtering based on items and collaborative filtering based on consumers. The collaborative filtering based on items obtains similarity of different items from their scores provided by same consumers and make recommendations according to the similarity of items. II. IDENTIFY, RESEARCH AND COLLECT IDEA 1) Why Recommendation is important? Recommender engines (REs) also known as recommender systems are software tools and techniques providing suggestions to a user. The suggestions provided are aimed at supporting their users in various decision making processes such as what items to buy, what music to listen, what profiles to browse, or what news to read. This thesis studies the feasibility of the integration of a recommender engine as a module in a News portal, and shows the process of its design and implementation using the Apache Mahout library. As such our work tackles two major problems which are: (1) the implementation of the recommender engine using the Apache Mahout library, and (2) the integration of the recommender in News portal.