Multi-agent web recommendations

Abstract

Due to the large amount of pages in Websites it is important to collect knowledge about users' previous visits in order to provide patterns that allow the customization of the Website. In previous work we proposed a multiagent approach using agents with two different algorithms (associative rules and collaborative filtering) and showed the results of the offline tests. Both algorithms are incremental and work with binary data. In this paper we present the results of experiments held online. Results show that this multi-agent approach combining different algorithms is capable of improving user's satisfaction. © Springer International Publishing Switzerland 2014.