Under CopyrightSchnürch, SimonSimonSchnürch2022-08-022022-08-022022978-3-8396-1831-8https://publica.fraunhofer.de/handle/publica/419254https://doi.org/10.24406/publica-19210.24406/publica-192This thesis offers a thorough review of stochastic mortality models, including various calibration and forecasting procedures. As a new contribution to the literature, machine learning methods are applied, yielding fresh perspectives on mortality data and improved forecasting performance. Benefits of classical models such as interpretability and prediction uncertainty quantification are preserved as much as possible or even enhanced.enMortality modelingMachine learningMortality shocksLee-Carter modelNeural networksDDC::500 Naturwissenschaften und Mathematik::510 Mathematik::519 Wahrscheinlichkeiten, angewandte Mathematikdoctoral thesis