For many years, the main goal of the Netflix recommendation engine has been to get the right titles in front of each member at the right time. Today, we use nonlinear, probabilistic and deep learning approaches to make better and better rankings of our movies and TV shows for each user. But the job of recommendation does not end there. The homepage should be able to convey to the member enough evidence of why this is a good title for her, especially for shows that the member has never heard of. One way to address this challenge is to personalize the way we portray the titles on our service. Our image personalization engine is driven by online learning and contextual bandits. Traditional bandits frameworks make strong assumptions which do not apply when predictions entail actions in the real world. We will discuss how learning algorithms can be augmented to better deal with causality, bias, and noncompliance.
Tony Jebara is Director of Machine Learning at Netflix and is sabbatical professor at Columbia University. He served as general chair of the 2017 International Conference on Machine Learning. He has published over 100 scientific articles in the field of machine learning and has received several best paper awards. He has co-founded and advised multiple AI startups.