Micro Level Prediction of Out-standing Claim Counts Based on Novel Mixture Models and Neural Networks (Gauss Prize 2023)

The main prize (endowed with 3,000 euros) was awarded to Prof. Dr. Axel Bücher and Alexander Rosenstock from Ruhr University Bochum for their article "Micro level prediction of out-standing claim counts based on novel mixture models and neural networks". In it, the research duo discusses the prediction of the number of outstanding claims in actuarial loss reserving and proposes a new approach based on a model for reporting delays at micro level and using neural networks. "The prediction of the number of outstanding claims (IBNR) is a central problem in actuarial loss reserving," explains Prof. Dr. Alfred Müller, Chairman of the Prize Committee. "The new approach provided here is therefore enormously helpful for actuaries."