Design, development and deployment of an intelligent, personalized recommendation system

Personalization and recommendation systems are a solution to the problem of content overload, especially in large information systems. In this thesis, a personalized recommendation system enhanced with semantic knowledge has been developed in order to overcome the most common limitations of traditional approaches: the cold-start and the sparsity problems. The recommender consists of the following two main components. A user-profile learning algorithm combines user’s feedback from different channels and employs domain inferences to construct accurate user profiles. A recommendation algorithm, using content-based filtering, exploits the semantic structure of the domain to obtain accurate predictions and generate the corresponding recommendations. The system’s design proposed is flexible enough to be potentially applied to applications of any domain that can be properly described using ontologies. In addition to the development of the recommendation system, an existing Web-application in the tourism domain has been extended and adapted in order to be able to integrate the recommender into it. The overall recommendation system has been evaluated and the results obtained indicate that it satisfies the requirements established.