Case-based reasoning as a prediction strategy for hybrid recommender systems

Hybrid recommender systems are capable of providing better recommendations than non-hybrid ones. Our approach to hybrid recommenders is the use of prediction strategies that determine which prediction technique(s) should be used at the moment an actual prediction is required. In this paper, we determine whether case-based reasoning can provide more accurate prediction strategies than rule-based predictions strategies created manually by experts. Experiments show that case-based reasoning can indeed be used to create prediction strategies; it can even increase the accuracy of the recommender in systems where the accuracy of the used prediction techniques is highly spread.