Fast context-aware recommendations with factorization machines

Abstract

The situation in which a choice is made is an important information for recommender systems. Context-aware rec- ommenders take this information into account to make pre- dictions. So far, the best performing method for context- aware rating prediction in terms of predictive accuracy is Multiverse Recommendation based on the Tucker tensor fac- torization model. However this method has two drawbacks: (1) its model complexity is exponential in the number of con- text variables and polynomial in the size of the factorization and (2) it only works for categorical context variables. On the other hand there is a large variety of fast but specialized recommender methods which lack the generality of context- aware methods. We propose to apply Factorization Machines (FMs) to model contextual information and to provide context-aware rating predictions. This approach results in fast context- aware recommendations because the model equation of FMs can be computed in linear time both in the number of con- text variables and the factorization size. For learning FMs, we develop an iterative optimization method that analyti- cally finds the least-square solution for one parameter given the other ones. Finally, we show empirically that our ap- proach outperforms Multiverse Recommendation in predic- tion quality and runtime.