Efficient Use of Data for LSTM Mortality Forecasting

31 Pages Posted: 6 Apr 2021

Date Written: March 16, 2021

Abstract

We consider a simple long-short term memory (LSTM) neural network extension of the Poisson Lee-Carter model, with a particular focus on different procedures for how to use training data efficiently, combined with ensembling to stabilise the predictive performance. We compare the standard approach of withholding the last fraction of observations for validation, with two other approaches: sampling a fraction of observations randomly in time; and splitting the population into two parts by sampling individual life histories. We provide empirical and theoretical support for using these alternative approaches.

Furthermore, to improve the stability of long-term predictions, we consider boosted versions of the Poisson Lee-Carter LSTM. In the numerical illustrations it is seen that even in situations where mortality rates are essentially log-linear as a function of calendar time, the boosted model does not perform significantly worse than a simple random walk with drift, and when non-linearities are present the predictive performance is improved. Moreover, boosting allows us to obtain reasonable model calibrations based on as few data points as 20 years.

Keywords: sequential neural networks, mortality forecasting, ensemble models, boosting, Lee-Carter model

Suggested Citation

Lindholm, Mathias and Palmborg, Lina, Efficient Use of Data for LSTM Mortality Forecasting (March 16, 2021). Available at SSRN: https://ssrn.com/abstract=3805843 or http://dx.doi.org/10.2139/ssrn.3805843

Mathias Lindholm

Stockholm University ( email )

Universitetsvägen 10
Stockholm, Stockholm SE-106 91
Sweden

Lina Palmborg (Contact Author)

Stockholm University ( email )

Universitetsvägen 10
Stockholm, Stockholm SE-106 91
Sweden

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
91
Abstract Views
356
rank
360,844
PlumX Metrics