Netflix at Qcon SFNov 7, 2018
We really enjoyed participating in QCon SF this year, and had speakers and host tracks from a number of different teams at Netflix. Here are a few highlights from our machine learning teams:
Ville Tuulos, an engineer on our machine learning infrastructure team, gave a talk about about human centric ML infrastructure. Many existing open-source machine learning frameworks are great at making advanced modeling possible. The job of our ML infrastructure is to make it remarkably easy to apply these frameworks to real business problems at Netflix. We have found that this requires an infrastructure that covers the day-to-day challenges of data scientists holistically, from understanding input data to building trust with consumers of models, not just the parts that are directly related to fitting and scoring models. He talked about the techniques and underlying principles driving our approach, which you'll be able to adapt and apply to your own use cases. You can view the slides here.
Justin Basilico, a research director for our page algorithms team, gave a talk on artwork personalization at Netflix. In this talk, he presented an approach for personalizing the artwork we show for each title on the Netflix homepage. He looks at how to frame this as a machine learning problem using contextual multi-armed bandits in a recommendation system setting. He also describes the algorithmic and system challenges involved in getting this type of approach for artwork personalization to succeed at Netflix scale. You can view the slides here.
Netflix sponsored the Women & Allies in Tech Breakfast, which was a great opportunity to network with smart women from different industries. We were pleased to hear that a portion of the sponsorship money provided will be used to grant QCon scholarships to 12 women and/or members of under-represented groups.