Denny Stohr


“Improving the Netflix Streaming Experience with Bayesian Optimization”


The video streaming system of Netflix has hundreds of configuration parameters that influence many aspects of the playback behavior when using our service; for example, such configurations specify the amount of video content to load before we begin playback to balance play delay and risk of rebuffers.

Usually, we perform many iterations of A/B experiments to fine-tune these values and provide the best possible user experience across the wide range of platforms and networks we serve worldwide. Still, identifying good configurations that work well across diverse networks and devices, in particular when dealing with multi-dimensional parameters, is challenging given their complex interactions with streaming metrics we observe in experimentation.

To help with these challenges, one powerful approach we have evaluated in the last years is Bayesian optimization. With this method, we can efficiently explore and understand the relationship between configuration parameters and objective metrics by building a surrogate model that incorporates experimental observations and guides future experiments. In this presentation, we give a brief introduction to the video streaming system of Netflix followed by an example use case on how we use Bayesian optimization in conjunction with our A/B experimentation framework to deliver concrete service improvements for our users.


Denny Stohr

After obtaining a B.Sc and M.Sc. in Information Systems at the University of Mannheim, Denny started a Ph.D. program at TU Darmstadt with the chair for Multimedia Communications as a researcher for the SFB MAKI. In 2018 he obtained a Ph.D. in Computer Science for his work on “User-centric Video in the Future Internet”. The same year, Denny moved to California to pursue a role at Netflix where he is currently working as a Senior Software Engineer in the Adaptive Streaming team. Here, his focus is on innovation in the intersection between Content Delivery, Encoding, and Streaming Algorithms to ultimately deliver concrete QoE improvements for Netflix customers on the TV and Android platforms.