Time-series forecasting of mortality rates using deep learning

DOI10.1080/03461238.2020.1867232zbMath1471.91480OpenAlexW3133800526MaRDI QIDQ4959368

Salvatore Scognamiglio, Ronald Richman, Mario V. Wüthrich, Francesca Perla

Publication date: 13 September 2021

Published in: Scandinavian Actuarial Journal (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/03461238.2020.1867232

zbMATH Keywords

recurrent neural networksLee-Carter modelmortality forecastingconvolutional neural networksrepresentation learningtime-series forecastinghuman mortality database

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Mathematical geography and demography (91D20) Actuarial mathematics (91G05)

Related Items (11)

Modelling mortality by continuous benefit amount ⋮ EXTENDING THE LEE–CARTER MODEL WITH VARIATIONAL AUTOENCODER: A FUSION OF NEURAL NETWORK AND BAYESIAN APPROACH ⋮ POINT AND INTERVAL FORECASTS OF DEATH RATES USING NEURAL NETWORKS ⋮ Efficient use of data for LSTM mortality forecasting ⋮ Non-Life Insurance Risk Classification Using Categorical Embedding ⋮ A Neural Approach to Improve the Lee-Carter Mortality Density Forecasts ⋮ Time-series forecasting of mortality rates using transformer ⋮ Intergenerational actuarial fairness when longevity increases: amending the retirement age ⋮ NEIGHBOURING PREDICTION FOR MORTALITY ⋮ CALIBRATING THE LEE-CARTER AND THE POISSON LEE-CARTER MODELS VIA NEURAL NETWORKS ⋮ LocalGLMnet: interpretable deep learning for tabular data

Uses Software

• LSTM
• ElemStatLearn
• Human Mortality
• Keras
• ASCL
• Adam

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Modeling and Forecasting U.S. Mortality
• A common age effect model for the mortality of multiple populations
• Robust forecasting of mortality and fertility rates: a functional data approach
• A Poisson log-bilinear regression approach to the construction of projected lifetables.
• Lee-Carter mortality forecasting with age-specific enhancement.
• A cohort-based extension to the Lee-Carter model for mortality reduction factors
• A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction
• On fitting generalized linear and non-linear models of mortality
• 10.1162/153244303322533223
• DYNAMIC PRINCIPAL COMPONENT REGRESSION: APPLICATION TO AGE-SPECIFIC MORTALITY FORECASTING
• A Quantitative Comparison of Stochastic Mortality Models Using Data From England and Wales and the United States
• FORECASTING MULTIPLE FUNCTIONAL TIME SERIES IN A GROUP STRUCTURE: AN APPLICATION TO MORTALITY
• WAVELET-BASED FEATURE EXTRACTION FOR MORTALITY PROJECTION
• MULTIVARIATE LONG-MEMORY COHORT MORTALITY MODELS

This page was built for publication: Time-series forecasting of mortality rates using deep learning