Seção: ArtigosTítulo: Transfer learning in the actuarial domain : foundations and applications / Youngsun Kim and Daniel BauerAutor: Kim, Youngsun Notas: Sumario: The article systematically analyzes the use of transfer learning in the actuarial field, particularly in the prediction of claim frequency when labeled data are scarce. It presents formal definitions, typologies, and methodological approaches, linking them to classical concepts such as credibility theory. Through empirical applications in automobile insurance, instance-based, feature-based, and parameter-based methods are evaluated. The results show improvements in accuracy and stability compared to traditional models. The study positions transfer learning as a relevant tool for modern actuarial analysisRegistros relacionados: En: North American actuarial journal. - Schaumburg : Society of Actuaries, 1997- = ISSN 1092-0277. - 16/03/2026 Tomo 30 Número 1 - 2026 , 23 p.Materia / lugar / evento: Cálculo actuarialMachine learningModelos predictivosSeguro de automóvilesInteligencia artificialOtros autores: Bauer, DanielOutras classificações: 6Direitos: In Copyright (InC)
