MOVIES2GO - A new approach to online movie recommendation

We are developing a web-based movie recommender system that catches and reasons with user preferences to pro-actively recommend movies. It combines voting based ranking procedure with guaranteed properties that use syntactic features like actor/actress of movies together with a learning based approach that processes semantic features of movies like its synopsis. Our primary concern is to develop a reasoning procedure that can meaningfully and systematically tradeoff between user preferences. We also provide multiple query modalities by which the user can pose unconstrained, constrained, or instance-based queries. In the paper, we outline the current status of our implementation with particular emphasis on the mechanisms used to provide robust and effective recommendations. We also incorporate some extensions to our previous work including learning modules, explanation facilities, and pro-active information gathering.