A Nonparametric Latent Factor Model For Location-Aware Video Recommendations
This work addresses personalized video recommendations for streaming services like Netflix, but it appears incremental as it applies existing Bayesian nonparametric techniques to a specific domain.
The paper tackled the problem of learning customers' video preferences from viewing patterns and geographical location using a Bayesian latent factor model, and results on a large Netflix dataset showed it captured interesting relationships between viewing and location.
We are interested in learning customers' video preferences from their historic viewing patterns and geographical location. We consider a Bayesian latent factor modeling approach for this task. In order to tune the complexity of the model to best represent the data, we make use of Bayesian nonparameteric techniques. We describe an inference technique that can scale to large real-world data sets. Finally we show results obtained by applying the model to a large internal Netflix data set, that illustrates that the model was able to capture interesting relationships between viewing patterns and geographical location.