Théo Verhelst

I am a postdoc researcher at the European Space Agency's Advanced Concepts Team (ACT). My research focuses on causal machine learning, and I am also interested in probability, information theory, physics, and more. Causal inference allows to formulate causal questions (is A a cause of B?), which represents a paradigm shift from traditional statistics (A is associated with B). Causal machine learning consists in leveraging the capabilities of machine learning models to answer causal queries, and in improving machine learning models with causal insights.

I studied computer science (BSc & MSc) at the Université Libre de Bruxelles (ULB) in Belgium. During my master I spent a year as Erasmus student at the University of Southampton, UK, where I studied artificial intelligence. Then, I did my PhD at ULB working in the Machine Learning Group under the supervision of Gianluca Bontempi. My PhD is on the inference of individual treatment effects (or uplift) for direct marketing campaigns in the telecom industry, done in partnership with Orange Belgium. You can read it here.

When I'm not reading papers, you can find me doing sports (martial arts, climbing), playing the piano, writing music, or writing spreadsheets to find optimal strategies in video-games.

You can find more info on my cool personnal website, which contains links to Google Scholar, GitHub, and other things. You can also reach me directly by email at tni.ase@tslehrev.oeht.