Targeting more relevant, contextual recommendations by exploiting domain knowledge

Abstract

In today's mobile applications, it becomes more and more important to have a broader view on knowledge about a certain domain when generating contextual and semantic recommendations. Data that provides additional and useful information to the traditional User x Item representation, such as taxonomies, implicit and indirect knowledge about a user's preferences or location information can immensely enhance the quality of recommendations. For this purpose, the generic recommender system of Fraunhofer Institute FOKUS, the SMART Recommendations Engine, has been extended by the SMART Ontology Extension and the Proximity Filter, which enable the recommender to use domain knowledge included in semantic ontologies and contextual information in the recommendation process in order to generate much more precise recommendations. The functionality of the extensions are demonstrated in the scope of a food purchase scenario. © 2010 ACM.