Title:
Experimentation at Spotify
Abstract:
In order to fuel product development, Spotify runs hundreds of concurrent experiments at any point in time. Large-scale A/B tests enable the product teams to gain causal insights on what works well and what does not.
This talk will give an introduction of experimentation at Spotify. We will outline a typical experimentation workflow, discuss major technical challenges as well as how we address them, and do a deep-dive into some of the foundational statistical concepts.
Short-Bio:
Michael is a Software Engineer at Spotify. In this role, he contributes to the development of Spotify's new experimentation platform. Before joining Spotify, he was a Data Scientist at the SAP Innovation Center Network. He holds a doctorate degree (Dr.-Ing.) in Computer Science from TU Darmstadt, where he worked as a researcher in the SFB MAKI for multiple years.
