Construction of Mortality Tables using Bidirectional LSTM Neural Networks to Predict Death Probabilities

Bibliographic Details
Main Author: Nascimento, José Douglas
Publication Date: 2022
Other Authors: Escovedo, Tatiana, Kalinowski, Marcos
Format: Article
Language: por
Source: Brazilian Journal of Information Systems
Download full: https://journals-sol.sbc.org.br/index.php/isys/article/view/2230
Summary: Mortality Tables are tables structured with mortality data, especially mortality rates observed at all ages, used in pension funds and life insurance markets. This article concerns the application of the neural network model to the construction of future mortality tables, using the Lee-Carter model for comparison. The proposed model was a LSTM (Long-Short Term Memory) Neural Network model, including a bidirectional variation. This network is characterized by the sequential processing of data over time. The data for the prediction came from historical mortality table data prepared by the IBGE (Brazilian Institute of Geography and Statistics) and the Human Mortality Database. The results point to a reasonable use as an auxiliary tool for predicting death probabilities.
id SBC-5_d5467aebd8d87a9f9e0f23f8084ff396
oai_identifier_str oai:journals-sol.sbc.org.br:article/2230
network_acronym_str SBC-5
network_name_str Brazilian Journal of Information Systems
repository_id_str
spelling Construction of Mortality Tables using Bidirectional LSTM Neural Networks to Predict Death ProbabilitiesConstrução de Tábuas de Mortalidade com o uso de Redes Neurais LSTM Bidirectional para Predição das Probabilidades de MorteMortality TablePension FundsLife ExpectancyForecastLee-Carter ModelNeural NetworkLSTMTábua de MortalidadePrevidênciaExpectativa de VidaPrevisãoModelo Lee-CarterRedes NeuraisLSTMMortality Tables are tables structured with mortality data, especially mortality rates observed at all ages, used in pension funds and life insurance markets. This article concerns the application of the neural network model to the construction of future mortality tables, using the Lee-Carter model for comparison. The proposed model was a LSTM (Long-Short Term Memory) Neural Network model, including a bidirectional variation. This network is characterized by the sequential processing of data over time. The data for the prediction came from historical mortality table data prepared by the IBGE (Brazilian Institute of Geography and Statistics) and the Human Mortality Database. The results point to a reasonable use as an auxiliary tool for predicting death probabilities.As Tábuas de Mortalidade são tabelas estruturadas contendo dados epidemiológicos traduzidos em probabilidades de morte associada a cada idade de vida, utilizadas no mercado de previdência e seguros. Este artigo discorre sobre a aplicação do modelo de redes neurais para a construção de tábuas de mortalidade futuras, tendo como comparação o modelo Lee-Carter. O modelo proposto foi a Rede LSTM (Long-Short Term Memory), sendo implementada também uma variação bidirecional. Esta rede tem como característica o processamento sequencial de dados ao longo do tempo. Os dados para a predição são oriundos de dados históricos de tábuas de mortalidade elaboradas pelo IBGE (Instituto Brasileiro de Geografia e Estatística) e do The Human Mortality Database. Os resultados apontam para uma utilização razoável como ferramenta auxiliar de predição das probabilidades de morte.Sociedade Brasileira de Computação2022-10-18info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://journals-sol.sbc.org.br/index.php/isys/article/view/223010.5753/isys.2022.2230iSys - Revista Brasileira de Sistemas de Informação; v. 15 n. 1 (2022); 9:1-9:24iSys - Brazilian Journal of Information Systems; Vol. 15 No. 1 (2022); 9:1-9:241984-290210.5753/isys.2022.1reponame:Brazilian Journal of Information Systemsinstname:Sociedade Brasileira de Computação (SBC)instacron:SBCporhttps://journals-sol.sbc.org.br/index.php/isys/article/view/2230/1933Copyright (c) 2022 The authorshttps://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessNascimento, José DouglasEscovedo, TatianaKalinowski, Marcos2022-10-18T22:43:17Zoai:journals-sol.sbc.org.br:article/2230Revistahttps://journals-sol.sbc.org.br/index.php/isys/ONGhttps://journals-sol.sbc.org.br/index.php/isys/oaipublicacoes@sbc.org.br1984-29021984-2902opendoar:2022-10-18T22:43:17Brazilian Journal of Information Systems - Sociedade Brasileira de Computação (SBC)false
dc.title.none.fl_str_mv Construction of Mortality Tables using Bidirectional LSTM Neural Networks to Predict Death Probabilities
Construção de Tábuas de Mortalidade com o uso de Redes Neurais LSTM Bidirectional para Predição das Probabilidades de Morte
title Construction of Mortality Tables using Bidirectional LSTM Neural Networks to Predict Death Probabilities
spellingShingle Construction of Mortality Tables using Bidirectional LSTM Neural Networks to Predict Death Probabilities
Nascimento, José Douglas
Mortality Table
Pension Funds
Life Expectancy
Forecast
Lee-Carter Model
Neural Network
LSTM
Tábua de Mortalidade
Previdência
Expectativa de Vida
Previsão
Modelo Lee-Carter
Redes Neurais
LSTM
title_short Construction of Mortality Tables using Bidirectional LSTM Neural Networks to Predict Death Probabilities
title_full Construction of Mortality Tables using Bidirectional LSTM Neural Networks to Predict Death Probabilities
title_fullStr Construction of Mortality Tables using Bidirectional LSTM Neural Networks to Predict Death Probabilities
title_full_unstemmed Construction of Mortality Tables using Bidirectional LSTM Neural Networks to Predict Death Probabilities
title_sort Construction of Mortality Tables using Bidirectional LSTM Neural Networks to Predict Death Probabilities
author Nascimento, José Douglas
author_facet Nascimento, José Douglas
Escovedo, Tatiana
Kalinowski, Marcos
author_role author
author2 Escovedo, Tatiana
Kalinowski, Marcos
author2_role author
author
dc.contributor.author.fl_str_mv Nascimento, José Douglas
Escovedo, Tatiana
Kalinowski, Marcos
dc.subject.por.fl_str_mv Mortality Table
Pension Funds
Life Expectancy
Forecast
Lee-Carter Model
Neural Network
LSTM
Tábua de Mortalidade
Previdência
Expectativa de Vida
Previsão
Modelo Lee-Carter
Redes Neurais
LSTM
topic Mortality Table
Pension Funds
Life Expectancy
Forecast
Lee-Carter Model
Neural Network
LSTM
Tábua de Mortalidade
Previdência
Expectativa de Vida
Previsão
Modelo Lee-Carter
Redes Neurais
LSTM
description Mortality Tables are tables structured with mortality data, especially mortality rates observed at all ages, used in pension funds and life insurance markets. This article concerns the application of the neural network model to the construction of future mortality tables, using the Lee-Carter model for comparison. The proposed model was a LSTM (Long-Short Term Memory) Neural Network model, including a bidirectional variation. This network is characterized by the sequential processing of data over time. The data for the prediction came from historical mortality table data prepared by the IBGE (Brazilian Institute of Geography and Statistics) and the Human Mortality Database. The results point to a reasonable use as an auxiliary tool for predicting death probabilities.
publishDate 2022
dc.date.none.fl_str_mv 2022-10-18
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://journals-sol.sbc.org.br/index.php/isys/article/view/2230
10.5753/isys.2022.2230
url https://journals-sol.sbc.org.br/index.php/isys/article/view/2230
identifier_str_mv 10.5753/isys.2022.2230
dc.language.iso.fl_str_mv por
language por
dc.relation.none.fl_str_mv https://journals-sol.sbc.org.br/index.php/isys/article/view/2230/1933
dc.rights.driver.fl_str_mv Copyright (c) 2022 The authors
https://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Copyright (c) 2022 The authors
https://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Sociedade Brasileira de Computação
publisher.none.fl_str_mv Sociedade Brasileira de Computação
dc.source.none.fl_str_mv iSys - Revista Brasileira de Sistemas de Informação; v. 15 n. 1 (2022); 9:1-9:24
iSys - Brazilian Journal of Information Systems; Vol. 15 No. 1 (2022); 9:1-9:24
1984-2902
10.5753/isys.2022.1
reponame:Brazilian Journal of Information Systems
instname:Sociedade Brasileira de Computação (SBC)
instacron:SBC
instname_str Sociedade Brasileira de Computação (SBC)
instacron_str SBC
institution SBC
reponame_str Brazilian Journal of Information Systems
collection Brazilian Journal of Information Systems
repository.name.fl_str_mv Brazilian Journal of Information Systems - Sociedade Brasileira de Computação (SBC)
repository.mail.fl_str_mv publicacoes@sbc.org.br
_version_ 1832110917158961152

Similar Items