Mortality improvement neural-network models with autoregressive effects

In this paper, we propose a neural network (NN) architecture of mortality improvement model with cohort effect. We then extend the mortality improvement NN model to consider autoregressive effects, which allows mortality improvement to depend on the lagged mortality rates. The advantage of our NN mo...

Full description

Saved in:
Bibliographic Details
Published in:Geneva papers on risk and insurance. Issues and practice 2024-04, Vol.49 (2), p.363-383
Main Authors: Hsiao, Hung-Tsung, Wang, Chou-Wen, Liu, I.-Chien, Kung, Ko-Lun
Format: Article
Language:English
Subjects:
Accuracy
Age
Deep learning
Economics and Finance
Finance
Forecasting
Insurance
Machine learning
Mortality
Neural networks
Risk Management
Trends
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose a neural network (NN) architecture of mortality improvement model with cohort effect. We then extend the mortality improvement NN model to consider autoregressive effects, which allows mortality improvement to depend on the lagged mortality rates. The advantage of our NN model setup is that the parameters of period and cohort effects are implicitly estimated by the NN models, and hence, the mortality projection can be obtained without taking the extra steps of selecting and estimating the suitable time-series model for period and cohort effects. Our empirical results suggests that, based on 48 populations in the Human Mortality Database with complete sets of observations from 1950 with the age span of 55–90, the NN models with cohort and autoregressive effects improve the forecast accuracy of mortality rate projections and provide better prediction performance.
ISSN:1018-5895
1468-0440
DOI:10.1057/s41288-024-00321-4