Building User profiles for Recommender Systems from incomplete preference relations

In recent years, in the e-commerce area new methods and tools have arisen in order to improve and customize the e-commerce Web sites according to users´ necessities and tastes. The most successful tool in this field have been the recommender systems. The aim of them is to assist people to find the best alternatives that satisfy their necessities using recommendations, leading them to interesting items, or hiding those useless and unattractive ones. Sometimes these systems face situations where there is a lack of information and this implies unsuccessful results. Although some solutions have been proposed, they present some limitations and drawbacks. In this contribution we present a knowledge-based recommender system that is able to compute successful recommendations using a few numbers of examples about the items that the users are looking for.