Research

My research lies at the intersection of business, technology, causal inference, and analytical modeling. I adopt a quantitative approach that combines empirical analysis with theoretical and analytical modeling to study complex economic and technological phenomena, with a particular emphasis on causal machine learning.

A primary focus of my work is the development and application of causal machine learning methods to study causal relationships in complex, high-dimensional settings. I apply these methods in digital marketing environments to analyze how interventions, such as mobile push notifications, affect user behavior. By combining experimental methods (e.g., A/B tests) with causal machine learning, I uncover heterogeneous treatment effects and improve data-driven decision-making through personalized targeting and on- and off-policy evaluation.

A second stream examines how emerging technologies disrupt established markets. Through analytical modeling and empirical analysis, I study how technological innovations, such as blockchain-based mechanisms like enforceable resale fees, reshape market structures and strategic interactions.

A third focus area concerns Human–AI interaction, particularly the role of uncertainty in AI-based decision support systems. Here, I study how uncertainty can be quantified, communicated, and incorporated into AI-based support processes to improve the reliability and adoption of AI systems.

Finally, I work on the application of statistical methods and machine learning in medical contexts. As part of the Volkswagen Foundation–funded project “From Machine Learning to Machine Teaching,” I analyze clinical data to better understand diseases such as post-COVID conditions and community-acquired pneumonia.

Causal Machine Learning  ·  Analytical Modelling  ·  Human-AI  ·  Medical Analytics