The joint project aims at developing a hybrid recommendation system. In a first phase a standard collaborative filtering approach for millions of user-generated data (implicit feedback while using a music streaming service) is developed. In parallel a content-based approach using semantic metadata and the underlying semantic graph structure is explored (Freebase, Musicbrainz). In a second phase both components are merged by late-fusion and we will try different hybridisation strategies which will be evaluated within explanation interfaces with real-world users.
Holistic / Hybrid Recommendation and Explanation:
We work on hybrid recommendation strategies since 2003. Recent interest of commercial music streaming services and internet radio stations enabled us to work close together with real-world use-cases. Nevertheless the issue is tough. In our opinon users demand explanations. For this reason we currently develop a hybrid recommender consisting of CF (user plays), social facets (facebook, etc.) and semantic metadata (hopefully using the graph structure) (Freebase, Musicbrainz). In a joint project with a German music streaming service we will try to evaluate different strategy settings (i.e the weigthings of the several components) and explanation interfaces with real-world users in 2013.