Hop on board of a project study on accounting fraud detection. These days, sophisticated fraud prediction models learn to differentiate between fraudulent and non-fraudulent firm-year observations based on training datasets for US listed firms. We are working on a project that applies such models far out of sample, i.e., on cases like Wirecard. The project study team will use news crawling and natural language processing to build up a rich dataset of accounting fraud instances outside the US. The suggested workflow will be important for regulating agencies like the BaFin. Send an email to matthias.regier(at)tum.de if you're interested in joining the team and would like to learn more about the scope.