Hong, LiangConformal prediction of future insurance claims in the regression problem / Liang HongSumario: The article presents a prediction method based on conformal prediction to estimate future insurance claims in regression settings. The proposed approach is fully model-free and tuning-parameter-free, ensuring finite-sample validity. It analyzes the limitations of traditional parametric and non-parametric approaches, such as model misspecification and the selection effect. Through simulation studies and a real case involving personal injury insurance claims, the effectiveness of the method is demonstrated, particularly in meeting Solvency II capital requirements. The approach is especially relevant for risk management and regulatory capital estimation in insurance companiesEn: European Actuarial Journal. - Cham, Switzerland : Springer Nature Switzerland AG, 2021-2022. - 13/04/2026 Número 16 issue 1 - abril 2026 , 17 p.1. Predicciones. 2. Modelos actuariales. 3. Solvencia II. 4. Seguros no vida. 5. Riesgo financiero. I. Springer. II. Title.
