Ricerc@Sapienza

Solvency capital requirements indicated by Solvency II against longevity risk involve distortions and inconsistencies caused by the invariance of the longevity shock compared to the age and time assumed by the regulatory model. To overcome the problem we introduce a temporal structure of the time mortality volatility which is included as a driver of longevity shock, by modelling a rolling window affine stochastic model.

Longevity risk management is an area of the life insurance business where the use of
Artificial Intelligence is still underdeveloped. The paper retraces the main results of the
recent actuarial literature on the topic to draw attention to the potential of Machine
Learning in predicting mortality and consequently improving the longevity risk quantification
and management, with practical implication on the pricing of life products
with long-term duration and lifelong guaranteed options embedded in pension contracts

Forecasting mortality is still a big challenge for Governments that are interested in reliable projections for defining their economic policy at local and national level. The accuracy of mortality forecasting is considered an important issue for longevity risk management. In the literature, many authors have analyzed the long-run relationship between mortality evolution and socioeconomic variables, such as economic growth, unemployment rate or educational level.