Context-Aware Bandits

We propose an efficient Context-Aware clustering of Bandits (CAB) algorithm,which can capture collaborative effects. CAB can be easily deployed in a real-world recommendation system, where multi-armed bandits have been shown toperform well in particular with respect to the cold-start problem. CAB utilizes acontext-aware clustering augmented by exploration-exploitation strategies. CABdynamically clusters the users based on the content universe under considera-tion. We give a theoretical analysis in the standard stochastic multi-armed ban-dits setting. We show the efficiency of our approach on production and real-worlddatasets, demonstrate the scalability, and, more importantly, the significant in-creased prediction performance against several state-of-the-art methods.