Generating B2C Recommendations Using a Fully Decentralized Architecture

In the last years, Business-to-Consumer (B2C) E-Commerce is playing a key role in the Web. In this scenario, recommender systems appear as a promising solution for both merchants and customers. However, in this context, the low scalability of the performances and the dependence on a centralized platform are two key problems to face. In this paper, we present a novel recommender system based on a multi-agent architecture, called Trader REcommender Systems (TRES). In TRES, the agents exploit their user’s profiles in their interaction, to make the merchants capable to generate effective and efficient recommendations. The architecture we have adopted is fully decentralized, giving to each merchant the capability to generate recommendations without requiring the help of any centralized computational unit. This characteristic, on the one hand, makes the system scalable with respect to the size of the users’ community. On the other hand, the privacy of each customer is preserved, since the merchant retrieves information about each customer simply monitoring the customer behaviour in visiting his site.To show the advantages introduced by the proposed approach some experimental results carried out by exploiting a prototype implemented in the JADE framework are presented.