Hi, I am Joel and welcome to my website.
I am a Research Scientist in the Machine Learning and Economics group at Spotify. My research focuses on statistical and machine learning methods for causal inference and decision making, with applications in marketing, health, platforms, and related areas transformed by digitalization and algorithms. At Spotify, I currently work on methods for heterogeneous treatment effects, contextual bandits, and off-policy evaluation to improve personalization and experimentation in large-scale recommender systems.
I hold a PhD from the Department of Management, Technology, and Economics at ETH Zurich, supervised by Stefan Feuerriegel and Florian von Wangenheim. During my doctorate, I did a research visit to the Operations, Information & Technology area at Stanford Graduate School of Business, hosted by Jann Spiess, and interned as Machine Learning Research Scientist at Booking.com in Amsterdam. I also joined the non-profit AI startup Algorithm Audit as a contributor on statistical methodology, which I continue to be involved in. Previously, I obtained double bachelor's and master's degrees in Statistics and Business & Economics from Lund University, Sweden, and worked on marketing mix modeling at GfK Nielsen and as Digital Strategist at an award-winning European digital advertising agency.
Research interests:
Causal Inference
Statistical Machine Learning
Data-Driven Decision-Making
Personalization and Digitalization
Application in Digital Marketing, Online Platforms, Health, and Public Policy