· 2016
Deep Neural Networks for YouTube Recommendations
- 3,415citations
- 2016year
Short summary
YouTube's recommendation system achieved dramatic performance improvements by adopting deep neural networks, specifically a two-stage approach involving deep candidate generation and deep ranking models.
AI-generated from the title and abstract; the full text is not read.
Key points
- YouTube's recommendation system now utilizes deep neural networks.
- The system is structured in two stages: candidate generation and ranking.
- Deep learning has led to dramatic performance improvements.
- Practical lessons from maintaining a massive recommendation system are shared.
AI-generated from the title and abstract; the full text is not read.
Abstract
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 designing, iterating and maintaining a massive recommendation system with enormous user-facing impact.
The authors' abstract, as published at the source., 2016 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Information Systems
Information SystemsComputer Science