Deep Neural Networks for YouTube Recommendations

@inproceedings{Covington2016DeepNN,
  title={Deep Neural Networks for YouTube Recommendations},
  author={Paul Covington and Jay L. Adams and Emre Sargin},
  booktitle={RecSys},
  year={2016}
}
YouTube represents one of the largest scale and most sophisticated industrial recommendation systems in existence. In this paper, we describe the system at a high level and focus on the dramatic performance improvements brought by deep learning. The paper is split according to the classic two-stage information retrieval dichotomy: first, we detail a deep candidate generation model and then describe a separate deep ranking model. We also provide practical lessons and insights derived from… CONTINUE READING