Transfer learning for mortality risk: A case study on the United Kingdom

Nalmpatian, Asmik; Heumann, Christian; Alkaya, Levent; Jackson, William (2025): Transfer learning for mortality risk: A case study on the United Kingdom. PLoS ONE, 20 (5): e0313378. ISSN 1932-6203

Abstract

This study introduces a transfer learning framework to address data scarcity in mortality risk prediction for the UK, where local mortality data is unavailable. By leveraging a pretrained model built from data across eight countries (excluding the UK) and incorporating synthetic data from the country most similar to the UK, our approach extends beyond national boundaries. This framework reduces reliance on local datasets while maintaining strong predictive performance. We evaluate the model using the Continuous Mortality Investigation (CMI) dataset and a Drift model to address discrepancies arising from local demographic differences. Our research bridges machine learning and actuarial science, enhancing mortality risk prediction and pricing strategies, particularly in data-poor settings.

• Doc-Type: Article (LMU)
• Organisational unit (Faculties): 16 Mathematics, Computer Science and Statistics > Statistics > Chairs/Working Groups > Methods for missing Data, Model selection and Model averaging
• DFG subject classification of scientific disciplines: Natural sciences
• DFG: Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) - 491502892