Securing collaborative filtering recommender system using Kohonen Net clustering technique

In recent era, the people find a variety of strategies to make choices about What to buy, Which movie to watch, and How to spend their leisure time. A system that overcomes the problem of “Information overload” in internet called “Recommender System”. Recommender system automates these strategies with the goal of providing affordable, personal and high quality recommendations. These Systems entirely depends on the ratings provided by the users to a particular item, Now a day´s collaborative recommender systems are susceptible to attacks i.e. A malevolent user might, for instance try to influence the behavior of the recommender system in such way that it includes a certain task of attack profile detection, using unsupervised learning. In this paper we study Artificial Neural Networks, especially a special kind of Neural Network called Kohonen Net Clustering.