search for

CrossRef (0)
6-Parametric factor model with long short-term memory
Communications for Statistical Applications and Methods 2021;28:521-536
Published online September 30, 2021
© 2021 Korean Statistical Society.

Janghoon Choi1,a

aKorea Insurance Research Institute, Korea
Correspondence to: 1 Korea Insurance Research Institute, 38 Gukjeguemyung-ro 6-gil, Youngdeungpo-gu, Seoul, Korea. E-mail: james021@gmail.com
Received April 15, 2021; Revised June 28, 2021; Accepted August 27, 2021.
As life expectancies increase continuously over the world, the accuracy of forecasting mortality is more and more important to maintain social systems in the aging era. Currently, the most popular model used is the Lee-Carter model but various studies have been conducted to improve this model with one of them being 6-parametric factor model (6-PFM) which is introduced in this paper. To this new model, long short-term memory (LSTM) and regularized LSTM are applied in addition to vector autoregression (VAR), which is a traditional time-series method. Forecasting accuracies of several models, including the LC model, 4-PFM, 5-PFM, and 3 6-PFM’s, are compared by using the U.S. and Korea life-tables. The results show that 6-PFM forecasts better than the other models (LC model, 4-PFM, and 5-PFM). Among the three 6-PFMs studied, regularized LSTM performs better than the other two methods for most of the tests.
Keywords : Lee Carter model, 6-PFM, accuracy test, vector autoregression, long short-term memory, regularized long short-term memory