Hybrid Recommendation Systems: A Case Study on the Movies Domain

Abstract

Recommendation systems have been used in e-commerce sites to make product recommendations and to provide customers with information that helps them decide which product to buy. They are based on different methods and techniques for suggesting products with the most well known being collaborative and content-based filtering. Recently, several recommendation systems adopted hybrid approaches by combining collaborative and content-based features as well as other techniques in order to avoid their limitations. In this chapter, we investigate hybrid recommendations systems and especially the way they support movie e-shops in their attempt to suggest movies to customers. Specifically, we introduce an approach where the knowledge about customers and movies is extracted from usage mining and ontological data in conjunction with customer-movie ratings and matching techniques between customers. This integration provides additional knowledge about customers’ preferences and allows the production of successful recommendations. Even in the case of the cold-start problem where no initial behavioural information is available, the approach can provide logical and relevant recommendations to the customers. The provided recommendations are expected to have higher accuracy in matching customers’ preferences and thus higher acceptance by them. Finally, we describe future trends and challenges and discuss the open issues in the field.