Delivery of video depends on a complex streaming ecosystem with many points of failure. For example, a publisher may fail to upload certain video assets; an ISP may experience congestion at several points in its network; or a home user may have a poor WiFi signal to their device.
Having gathered data on video quality from many kinds of playing devices across the United States, Conviva is able to attribute quality deteriorations to the different parts of this ecosystem. In this session, you’ll learn about the nature and scope of the data, Conviva’s use of machine learning models in fault attribution, their use of Apache Spark and Databricks, and their results.
Session hashtag: #SFml9
Oleg Vasilyev is a Senior Data Scientist at Conviva. He works on quality-engagement and predictive modeling projects, applying machine learning on Spark. He has decade long experience applying neural networks to images, health and financial profiles.
Henry Milner is a Senior Data Scientist at Conviva and a PhD student in Computer Science at UC Berkeley. His interests include distributed machine learning and data science education.