Attention-based Mixture Density Recurrent Networks for History-based Recommendation
This work addresses recommendation systems for users by explicitly handling multi-modal distributions, but it is incremental as it builds on existing attention and mixture density methods.
The paper tackles personalized history-based recommendation by modeling a multi-modal conditional distribution over items, achieving improved performance in precision, recall, and nDCG on MovieLens-20M and RecSys15 datasets.
The goal of personalized history-based recommendation is to automatically output a distribution over all the items given a sequence of previous purchases of a user. In this work, we present a novel approach that uses a recurrent network for summarizing the history of purchases, continuous vectors representing items for scalability, and a novel attention-based recurrent mixture density network, which outputs each component in a mixture sequentially, for modelling a multi-modal conditional distribution. We evaluate the proposed approach on two publicly available datasets, MovieLens-20M and RecSys15. The experiments show that the proposed approach, which explicitly models the multi-modal nature of the predictive distribution, is able to improve the performance over various baselines in terms of precision, recall and nDCG.