Taxonomy-Informed Latent Factor Models for Implicit Feedback

We describe an approach based on latent factor models to the Track 2 task of KDD Cup 2011, which required learning to discriminate between highly rated and unrated items from a large dataset of music ratings. We take the pairwise ranking route, training our models to rank the highly rated items above the unrated items which are sampled from the same distribution. Using the item relationship information from the provided taxonomy to constrain item representations results in improved predictive performance. Providing the model with features summarizing the user rating history as it relates to the item being ranked leads to further improvement.