A dynamic web recommender system based on cellular learning automata
Mojdeh Talabeigi, Rana Forsati, Mohammad Reza Meybodi · 2010
Different web recommendation systems have been proposed to address the problem of information overload on the Internet. They attempt to guide users toward interesting and useful items in a large information space. They anticipate the information needs of on-line users and provide them with recommendations to facilitate and personalize their navigation. There are many approaches to building such systems, but most of these systems are static which analyze information resources, discover patterns from this data and make recommendations based on the extracted knowledge. So they need to periodically update extracted pattern and rules in order to make sure they still reflect the trends of users or the changes of the site structure or content. In this paper we propose a dynamic web page recommender system based on asynchronous cellular learning automata (ACLA) which continuously interacts with the users and learns from his behavior. Furthermore, we try to use all factors which have influence on the quality of recommendation and might help system to be able to make more successful recommendations. The proposed system use web usage data and structure of the web site to learn user navigation patterns and predicting user's future requests. We evaluate our method under different settings. Our experiments on real data set show that our proposed system performs better than the other algorithm we compared to and show how this method can improve the overall quality of web recommendations.