I am a Research Scientist in the Personalization Economics group at Spotify. My research focuses on causal inference and data-driven decision-making using machine learning, with applications in the digital economy. I am particularly interested in developing methods and tools to solve problems in marketing, operations, and economics brought on by digitalization, such as personalization, algorithmic fairness, and the value of digital data and algorithms for decision making.

At Spotify, I collaborate with engineers and product teams to optimize our experimentation practices for content personalization and distribution on the Homepage. This involves adapting off-policy evaluation and bandit algorithms to balance their statistical performance against their economic outcomes for users, creators, and the platform.

I obtained my PhD in Management from ETH Zurich, supervised by Stefan Feuerriegel and Florian von Wangenheim. During my doctorate, I was a visiting PhD student in the Operations, Information and Technology area at Stanford Graduate School of Business hosted by Jann Spiess. I also interned as Machine Learning Research Scientist at Booking.com and joined the non-profit AI startup Algorithm Audit as Core Contributor on statistical methodology. I hold double B.Sc. and M.Sc. in Statistics and Business & Economics from Lund University in Sweden. Previously, I was part of the Marketing Science team at GfK, and worked on marketing analytics in digital advertising and educational technology.