Framework of Web Recommendation System For Browsing Behaviour Prediction
Sowmya K Menon1, Varghese Paul2

1Sowmya K Menon, Research Scholar, Bharathiar University, Coimbatore (Tamil Nadu), India.
2Varghese Paul, Professor, IT, CUSAT, Cochin (Kerala), India.
Manuscript received on 09 June 2019 | Revised Manuscript received on 30 June 2019 | Manuscript Published on 04 July 2019 | PP: 1093-1099 | Volume-8 Issue-1S4 June 2019 | Retrieval Number: A12040681S419/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Social networking is an important aspect in our day today life. In this era our main aim is to develop systems recommending good types of websites to users. As the changes in social networking is increasing day by day ,there should be the need for a system recommending the websites the user is having great interest. This paper focuses on recommending systems for browsing behavior prediction. Optimization of k-means code can be done using simulated annealing techniques. Simulated annealing is used to solve the problem of local minima. This function searches for global minimum of a very complex non-linear objective function with a very large number of optima. We are going to optimize k-means code by simulated annealing using the GENSA package present in the R-studio. After the clusters are made the system automatically recommends the clusters that are having the same browsing behavior patterns . Here we are analyzing the browsing habits of a group of users and these users are grouped into different clusters in the server so that we can predict these type of users who tend to browse the similar types of websites. The main idea used in the system is that it will recommend the websites that the users are frequently visiting. The implementation phase includes the entire system being loaded into a cloud framework of different users and a cloud server which is based on Google App Engine. The user belonging to the same cluster are recommended based on the browsing behavior. In this paper we focus on the optimization of k-means code using simulated annealing techniques. In order to get the accuracy, we just compare the browsing behavior of different users in the database and the websites the system will be going to recommend.. With our project we try to implement a movie recommendation system[15] which would provide the users with movie suggestions using Collaborative Filtering and Clustering algorithms building a model from a user’s past behavior (movies previously watched or selected and/or numerical ratings given to those movies) as well as similar decisions made by other users.
Keywords: Clustering, GENSA, Google App Engine, Recommendation System.
Scope of the Article: Patterns and Frameworks