Content-Aware Collaborative Music Recommendation Using Pre-trained Neural Networks

To incorporate content information into collab-orative filtering methods, we train a neural net-work on semantic tagging information as a con-tent model and use it as a prior in a collaborative filtering model. Such a system allows the user listening data to “speak for itself”. The proposed system is evaluated on the Million Song Dataset and shows performance comparably better than the collaborative filtering approaches, in addition to favorable results in the cold-start case. 1