Pesquisa de referências

A Neutral-network analyzer for mortality forecast

Recurso electrónico / electronic resource
Registro MARC
Tag12Valor
LDR  00000cab a2200000 4500
001  MAP20180022500
003  MAP
005  20180717154926.0
008  180712e20180501esp|||p |0|||b|eng d
040  ‎$a‎MAP‎$b‎spa‎$d‎MAP
084  ‎$a‎6
100  ‎$0‎MAPA20180010453‎$a‎Hainaut, Donatien
24512‎$a‎A Neutral-network analyzer for mortality forecast‎$c‎Donatien Hainaut
520  ‎$a‎This 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 effects
650 4‎$0‎MAPA20080555016‎$a‎Longevidad
650 4‎$0‎MAPA20080555306‎$a‎Mortalidad
650 4‎$0‎MAPA20080563790‎$a‎Predicciones
650 4‎$0‎MAPA20100065273‎$a‎Modelo Lee-Carter
650 4‎$0‎MAPA20080602659‎$a‎Modelos econométricos
650 4‎$0‎MAPA20080624842‎$a‎Redes neuronales artificiales
650 4‎$0‎MAPA20080579258‎$a‎Cálculo actuarial
651 1‎$0‎MAPA20080637880‎$a‎Francia
651 1‎$0‎MAPA20080638306‎$a‎Gran Bretaña
651 1‎$0‎MAPA20080638337‎$a‎Estados Unidos
7730 ‎$w‎MAP20077000420‎$t‎Astin bulletin‎$d‎Belgium : ASTIN and AFIR Sections of the International Actuarial Association‎$x‎0515-0361‎$g‎01/05/2018 Volumen 48 Número 2 - mayo 2018 , p. 481-508