Centro de Documentación de Fundación MAPFRE - A Neutral-network analyzer for mortality forecast

Notas: Sumario: This article proposes a neural-network approach to predict and simulate human mortality rates. This semi-parametric model is capable to detect and duplicate non-linearities observed in the evolution of log-forces of mortality. The method proceeds in two steps. During the first stage, a neural-network-based generalization of the principal component analysis summarizes the information carried by the surface of log-mortality rates in a small number of latent factors. In the second step, these latent factors are forecast with an econometric model. The term structure of log-forces of mortality is next reconstructed by an inverse transformation. The neural analyzer is adjusted to French, UK and US mortality rates, over the period 1946-2000 and validated with data from 2001 to 2014. Numerical experiments reveal that the neural approach has an excellent predictive power, compared to the LeeCarter model with and without cohort effectsRegistros relacionados: En: Astin bulletin. - Belgium : ASTIN and AFIR Sections of the International Actuarial Association = ISSN 0515-0361. - 01/05/2018 Volumen 48 Número 2 - mayo 2018 , p. 481-508Materia / lugar / evento: Longevidad Mortalidad Predicciones Modelo Lee-Carter Modelos econométricos Redes neuronales artificiales Cálculo actuarial Francia Gran Bretaña Estados Unidos Outras classificações: 6

Direitos: In Copyright (InC)

‌ Ver detalhe do número