Mortality improvement neural-network models with autoregressive effects

Hung-Tsung Hsiao, Chou-Wen Wang (), I.-Chien Liu and Ko-Lun Kung
Additional contact information
Hung-Tsung Hsiao: National Sun Yat-Sen University
Chou-Wen Wang: National Sun Yat-Sen University
I.-Chien Liu: National Taichung University of Science and Technology
Ko-Lun Kung: Feng Chia University

The Geneva Papers on Risk and Insurance - Issues and Practice, 2024, vol. 49, issue 2, No 8, 363-383

Abstract: Abstract 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.

Keywords: Mortality modelling; Neural networks; Mortality improvement; Autoregressive effect; Cohort effect (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1057/s41288-024-00321-4 Abstract (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:pal:gpprii:v:49:y:2024:i:2:d:10.1057_s41288-024-00321-4

Ordering information: This journal article can be ordered from
http://www.springer.com/finance/journal/41288/PS2

DOI: 10.1057/s41288-024-00321-4

Access Statistics for this article

The Geneva Papers on Risk and Insurance - Issues and Practice is currently edited by Christophe Courbage

More articles in The Geneva Papers on Risk and Insurance - Issues and Practice from Palgrave Macmillan, The Geneva Association Contact information at EDIRC.
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().