Extending the Lee-Carter model with variational autoencoder: A fusion of neural network and Bayesian approach

DOI10.1017/ASB.2022.15MaRDI QIDQ5045338zbMATH OpenOpenAlexFDO

Authors Akihiro Miyata, Naoki Matsuyama

Publication date 4 November 2022

Published in ASTIN Bulletin (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1017/asb.2022.15

zbMATH Keywords

Lee-Carter modelstate-space modelvariational Bayesian inferencevariational autoencoder

Mathematics Subject Classification ID

Actuarial mathematics (91G05)

Recommendations

• Calibrating the Lee-Carter and the Poisson Lee-Carter models via neural networks
• A Neural Approach to Improve the Lee-Carter Mortality Density Forecasts
• Point and interval forecasts of death rates using neural networks
• Extending Lee–Carter Mortality Forecasting
• Five different distributions for the Lee-Carter model of mortality forecasting: a comparison using GAS models

Cites work

• A Bayesian approach to pricing longevity risk based on risk-neutral predictive distributions
• A Bayesian forecasting model: predicting U.S. male mortality
• A Poisson log-bilinear regression approach to the construction of projected lifetables.
• A cohort-based extension to the Lee-Carter model for mortality reduction factors
• A gravity model of mortality rates for two related populations
• A neural-network analyzer for mortality forecast
• A quantitative comparison of stochastic mortality models using data from England and Wales and the United States
• Approximation by superpositions of a sigmoidal function
• Bayesian Poisson log-bilinear mortality projections
• Modeling and forecasting U.S. mortality. (With discussion)
• Neighbouring prediction for mortality
• Point and interval forecasts of death rates using neural networks
• Time-series forecasting of mortality rates using deep learning

Cited in

(4)

• Calibrating the Lee-Carter and the Poisson Lee-Carter models via neural networks
• The use of autoencoders for training neural networks with mixed categorical and numerical features
• Accurate and explainable mortality forecasting with the LocalGLMnet
• Parameter estimation and forecasts for an integrated Lee-Carter model

This page was built for publication: Extending the Lee-Carter model with variational autoencoder: A fusion of neural network and Bayesian approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5045338)