Data Intelligence with the Elastic Stack @ Scale: NVIDIA's User Experience Streaming Analytics

NVIDIA collects metrics for every frame streamed, every second spent on GeForce NOW, its streaming video game platform, using the Elastic Stack – enabling business, engineering, operations, and quality assurance teams to assess quality and debug issues in real time.

In this talk, Satish and Niranjan will provide an overview of the GeForce NOW data platform, built on Kafka, Spark, the Elastic Stack, and X-Pack, which handles billions of events every day, as well as give a demo-driven walk-through of their two main use cases: analyzing and enhancing user experience metrics for pre- & post- product launches, and visual logging providing automated {log}-to-dashboard functionality.

Satish Dandu

Satish Dandu is a Data Science & Engineering Manager at NVIDIA. At NVIDIA, he leads teams that build massive end-to-end big data & deep learning platforms, including real time analytics, data warehousing using big data engineering, and AI platforms using deep learning to improve user experience for millions of users. Prior to NVIDIA, Satish was leading data engineering teams at both startups and large public companies. His areas of interest are in building large scale engineering platforms, big data engineering, and deep learning. Satish has an MS in Computer Science from Univ. Of Houston.

Niranjan Nataraja

Niranjan Nataraja leads many data analytics efforts at NVIDIA where he has worked on capacity modeling for software build and test systems, queueing and simulation analysis, and anomaly detection using deep neural nets. He also has extensive experience building data applications in Elasticsearch, Kibana, and Spark for GeForce NOW to improve overall user experience. Prior to NVIDIA, Niranjan completed his Masters in Industrial Engineering at Texas A&M University with specialization in production economics using linear programming techniques.