A stochastic implementation of the APCI model for mortality projections

Stephen J. Richards, Iain David Currie, Torsten Kleinow, Gavin P. Ritchie

Research output: Contribution to journalArticle

Abstract

The Age-Period-Cohort-Improvement (APCI) model is a new addition to the canon of mortality forecasting models. It was introduced by Continuous Mortality Investigation as a means of parameterising a deterministic targeting model for forecasting, but this paper shows how it can be implemented as a fully stochastic model. We demonstrate a number of interesting features about the APCI model, including which parameters to smooth and how much better the model fits to the data compared to some other, related models. However, this better fit also sometimes results in higher value-at-risk (VaR)-style capital requirements for insurers, and we explore why this is by looking at the density of the VaR simulations.
Original languageEnglish
Article numbere13
JournalBritish Actuarial Journal
Volume24
DOIs
Publication statusPublished - 28 Mar 2019

Fingerprint

mortality
targeting
simulation

Cite this

Richards, Stephen J. ; Currie, Iain David ; Kleinow, Torsten ; Ritchie, Gavin P. / A stochastic implementation of the APCI model for mortality projections. In: British Actuarial Journal. 2019 ; Vol. 24.
@article{dc853118a4364399a4a24fc82e189864,
title = "A stochastic implementation of the APCI model for mortality projections",
abstract = "The Age-Period-Cohort-Improvement (APCI) model is a new addition to the canon of mortality forecasting models. It was introduced by Continuous Mortality Investigation as a means of parameterising a deterministic targeting model for forecasting, but this paper shows how it can be implemented as a fully stochastic model. We demonstrate a number of interesting features about the APCI model, including which parameters to smooth and how much better the model fits to the data compared to some other, related models. However, this better fit also sometimes results in higher value-at-risk (VaR)-style capital requirements for insurers, and we explore why this is by looking at the density of the VaR simulations.",
author = "Richards, {Stephen J.} and Currie, {Iain David} and Torsten Kleinow and Ritchie, {Gavin P.}",
year = "2019",
month = "3",
day = "28",
doi = "10.1017/S1357321718000260",
language = "English",
volume = "24",
journal = "British Actuarial Journal",
issn = "1357-3217",
publisher = "Cambridge University Press",

}

A stochastic implementation of the APCI model for mortality projections. / Richards, Stephen J.; Currie, Iain David; Kleinow, Torsten; Ritchie, Gavin P.

In: British Actuarial Journal, Vol. 24, e13, 28.03.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A stochastic implementation of the APCI model for mortality projections

AU - Richards, Stephen J.

AU - Currie, Iain David

AU - Kleinow, Torsten

AU - Ritchie, Gavin P.

PY - 2019/3/28

Y1 - 2019/3/28

N2 - The Age-Period-Cohort-Improvement (APCI) model is a new addition to the canon of mortality forecasting models. It was introduced by Continuous Mortality Investigation as a means of parameterising a deterministic targeting model for forecasting, but this paper shows how it can be implemented as a fully stochastic model. We demonstrate a number of interesting features about the APCI model, including which parameters to smooth and how much better the model fits to the data compared to some other, related models. However, this better fit also sometimes results in higher value-at-risk (VaR)-style capital requirements for insurers, and we explore why this is by looking at the density of the VaR simulations.

AB - The Age-Period-Cohort-Improvement (APCI) model is a new addition to the canon of mortality forecasting models. It was introduced by Continuous Mortality Investigation as a means of parameterising a deterministic targeting model for forecasting, but this paper shows how it can be implemented as a fully stochastic model. We demonstrate a number of interesting features about the APCI model, including which parameters to smooth and how much better the model fits to the data compared to some other, related models. However, this better fit also sometimes results in higher value-at-risk (VaR)-style capital requirements for insurers, and we explore why this is by looking at the density of the VaR simulations.

U2 - 10.1017/S1357321718000260

DO - 10.1017/S1357321718000260

M3 - Article

VL - 24

JO - British Actuarial Journal

JF - British Actuarial Journal

SN - 1357-3217

M1 - e13

ER -