Our image personalization engine is driven by online learning and contextual bandits to reliably handle over 20 million personalized image requests per second. One way to address this challenge is to personalize the way we portray the titles on our service. 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. But the job of recommendation does not end there. Today, we use nonlinear, probabilistic, and deep learning approaches to make even better rankings of our movies and TV shows for each user. For instance, the 2006 Netflix Challenge helped spur new research in low-rank matrix decomposition and collaborative filtering. Part of the Special ECE Seminar Series Modern Artificial Intelligence Title:įor many years, the main goal of the Netflix recommendation system has been to get the right titles in front of each member at the right time.
0 Comments
Leave a Reply. |