Machine Learning & Recommender Systems at Netflix Scale
We at Netflix strive to deliver maximum enjoyment and entertainment to our millions of members across the world. One of the keys for innovating and improving our product is to leverage the vast amounts of user feedback we receive from our members every day. In order to turn data into knowledge, and knowledge into measurable business value, we need to take a multilayered approach that includes the use of smart system architectures and powerful machine learning algorithms as well as a data-driven approach to product innovation.
In this talk you will hear about some of the machine learning algorithms that power our recommender systems and the kind of data and features that drive them. You will also get an insight into the innovation approach that includes offline experimentation and online AB testing. Finally, you will learn about the system architectures that enable all of this at a Netflix scale.