2017
DOI: 10.2139/ssrn.2921841
|View full text |Cite
|
Sign up to set email alerts
|

Machine Learning Techniques for Mortality Modeling

Abstract: Various stochastic models have been proposed to estimate mortality rates. In this paper we illustrate how machine learning techniques allow us to analyze the quality of such mortality models. In addition, we present how these techniques can be used for differentiating the different causes of death in mortality modeling.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
9
0
1

Year Published

2019
2019
2022
2022

Publication Types

Select...
3
1
1
1

Relationship

0
6

Authors

Journals

citations
Cited by 7 publications
(10 citation statements)
references
References 12 publications
(19 reference statements)
0
9
0
1
Order By: Relevance
“…It upheld by its history foundation utilizing a re-feeding care of instrument, in which an anticipated worth may fill in as a contribution for new expectations at further developed focuses in time. In condition ( 6 ) speaks to as anticipate arrangement y(t) given d past estimations of y(t).…”
Section: Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…It upheld by its history foundation utilizing a re-feeding care of instrument, in which an anticipated worth may fill in as a contribution for new expectations at further developed focuses in time. In condition ( 6 ) speaks to as anticipate arrangement y(t) given d past estimations of y(t).…”
Section: Methodsmentioning
confidence: 99%
“…Machine learning techniques also can be used to develop standard mortality models. Deprez et al ( 6 ) used machine learning algorithms to fit and assess the mortality model by detecting the weaknesses of different mortality models. Artificial Neural Networks (ANNs) ( 7 ) used to track and forecast latent mortality factors with greater predictability.…”
Section: Introductionmentioning
confidence: 99%
“…em que é o número de óbitos ocorridos entre as idades e + 1; é o número de óbitos esperados entre as idades e + 1. Assim, a estatística do teste ( ) é: Apesar de ser um teste recorrente na literatura, outras técnicas ainda mais robustas vêm sendo desenvolvidas no âmbito da modelagem para avaliar a qualidade de modelos e seus ajustes (Deprez et al 2017;Sakr et al, 2017;Richman, 2018). A capacidade de processamento de dados com o uso de tecnologias modernas permite maior acurácia dos modelos.…”
Section: Teste De Aderência E Medida De Acuráciaunclassified
“…[17]. Recent work in [14,42,46,47] aims to enhance the quality of parametric mortality models, such as the Lee-Carter model, by using models from machine learning and deep learning to calibrate them. This also contributes to a profound, multidisciplinary branch of research that utilizes neural networks as a modelling approach in Markov settings, see e.g.…”
Section: Introductionmentioning
confidence: 99%
“…Similarly to literature listed above, we utilize the class of neural networks to optimize our objective. However, in contrast to [14,42,46,47], we retrieve hidden Markov assumptions that an insurance company originally imposed when setting up the contracts. This information allows us to identify different profiles of policyholders in a portfolio, e.g.…”
Section: Introductionmentioning
confidence: 99%