I present a hybrid matrix factorisation model representing users and items as linear combinations of their content features' latent factors. The model outperforms both collaborative and content-based models in cold-start or sparse interaction data scenarios (using both user and item metadata), and performs at least as well as a pure collaborative matrix factorisation model where interaction data is abundant. Additionally, feature embeddings produced by the model encode semantic information in a way reminiscent of word embedding approaches, making them useful for a range of related tasks such as tag recommendations.
@article{arxiv.1507.08439,
title = {Metadata Embeddings for User and Item Cold-start Recommendations},
author = {Maciej Kula},
journal= {arXiv preprint arXiv:1507.08439},
year = {2015}
}