Collaborative Filtering with Recurrent Neural Networks
This work addresses movie recommendation for users, but it is incremental as it applies an existing method (LSTM) to a new interpretation of collaborative filtering.
The paper tackled collaborative filtering for movie recommendation by framing it as a sequence prediction problem and applying LSTM recurrent neural networks, showing that LSTM is competitive overall and largely outperforms other methods in item coverage and short-term predictions.
We show that collaborative filtering can be viewed as a sequence prediction problem, and that given this interpretation, recurrent neural networks offer very competitive approach. In particular we study how the long short-term memory (LSTM) can be applied to collaborative filtering, and how it compares to standard nearest neighbors and matrix factorization methods on movie recommendation. We show that the LSTM is competitive in all aspects, and largely outperforms other methods in terms of item coverage and short term predictions.