A Recommender System for Online Shopping Based on Past Customer Behaviour

With current projections regarding the growth of Internet sales, online retailing raises many questions about how to market on the Net. While convenience impels consumers to purchase items on the web, quality remains a significant factor in deciding where to shop online. The competition is increasing and personalization is considered to be the competitive advantage that will determine the winners in the market of online shopping in the following years. Recommender systems are a means of personalizing a site and a solution to the customer’s information overload problem. As such, many e-commerce sites already use them to facilitate the buying process. In this paper we present a recommender system for online shopping focusing on the specific characteristics and requirements of electronic retailing. We use a hybrid model supporting dynamic recommendations, which eliminates the problems the underlying techniques have when applied solely. At the end, we conclude with some ideas for further development and research in this area.