Construction of Mortality Tables using LSTM Neural Networks

  • José Douglas Nascimento PUC-Rio
  • Tatiana Escovedo PUC-Rio

Resumo


Mortality Table are tables structured with mortality database, especially mortality rates observed at all ages, used in pension funds and life insurance. This article based about application of neural network model to construction of forecast life tables comparing the performance of future model to Lee-Carter Model. Lee-Carter has been used in literature for fitting and forecasting the human mortality rates in mortality table. Architecture proposed was LSTM (Long-Short Term Memory) Network Neural model. LSTM Neural Networks are ideal for prediction of temporal sequences. Dates were collected through historical mortality tables information of IBGE (Instituto Brasileiro de Geografia e Estatística). Results providing plausible utilily of model LSTM Neural Network to approach to forecasting mortality rates.
Palavras-chave: Mortality Table, Pension Funds, Life Expectancy, Forecast, Projection, Lee-Carter Model, Neural Network, LSTM

Referências

Cordeiro Filho, Antônio, Cálculo atuarial aplicado: teoria e aplicações: exercícios resolvidos e propostos. 2. ed. -[3.Reimpr.]. São Paulo: Atlas, 2017. 

Newton L. Bowers Jr.; Hans U. Gerber; James C. Hickman; Donald Jones; Cecil J. Nesbitt, Actuarial Mathematics, The Society of Actuaries, 1986. 

Souza, Silney de, Seguros: contabilidade, atuária e auditoria. 2. ed. São Paulo: Saraiva, 2007.

Rodrigues, José Ângelo, Gestão de Risco Atuarial. 1. ed. São Paulo: Saraiva, 2008. 

London, C. and E. Layton; New York, The Spectator company; [etc, etc.], Transactions of the second International Actuarial Congress, held in the hall of the Institute of Actuaries, Staple Inn, Holborn, London, May 16 to 20, 1898, by International Congress of Actuaries (2nd : 1898 : London), 1899. Disponível em: https://archive.org/details/transactionsofse00interich. Acessado em: 20/09/2020.

Castro, Luciano Gonçalves de, Nota Técnica sobre a Metodologia adotada pelo Ministério da Previdência Social na Extrapolação das Tábuas de Mortalidade IBGE para as idades acima de 80 anos. Disponível em: [link]. Acessado em 20/09/2020 2014.

Lee, Ronald D., Carter, Laurence R., Modelling and Forecasting U.S. Mortality. Journal of the American Statistical Association 87, 659-671. 1992. 

Marius D. Pascariu, Vaupel, James W., Canudas–Romo, Vladimir. Modelling and forecasting mortality: The Double-Gap Life Expectancy Forecasting Model. University of Southern Denmark October, 2018. 

Escovedo, Tatiana e Koshiyama, Adriano, Introdução a Data Science - Algoritmos de Machine Learning e métodos de análise, Casa do Código, 2020. 

Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning. MIT Press; 2016. 

Zaccone, Giancarlo, Md. Rezaul Karim, & Ahmed Menshawy Deep Learning with TensorFlow. Birmingham: Packt Publishing, 2017. Print.

Chollet, François. Deep learning with Python. Shelter Island, NY: Manning Publications Co, 2018. Print.
Publicado
07/06/2021
NASCIMENTO, José Douglas; ESCOVEDO, Tatiana. Construction of Mortality Tables using LSTM Neural Networks. In: SIMPÓSIO BRASILEIRO DE SISTEMAS DE INFORMAÇÃO (SBSI), 17. , 2021, Uberlândia. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2021 .

##plugins.generic.recommendByAuthor.heading##