Author:
Wüthrich Mario V.,Merz Michael
Abstract
AbstractThis chapter considers recurrent neural (RN) networks. These are special network architectures that are useful for time-series modeling, e.g., applied to time-series forecasting. We study the most popular RN networks which are the long short-term memory (LSTM) networks and the gated recurrent unit (GRU) networks. We apply these networks to mortality forecasting.
Publisher
Springer International Publishing
Reference27 articles.
1. Brouhns, N., Denuit, M., & Vermunt, J. K. (2002). A Poisson log-bilinear regression approach to the construction of projected lifetables. Insurance: Mathematics & Economics, 31/3, 373–393.
2. Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv:1406.1078.
3. De Jong, P., Tickle, L., & Xu, J. (2020). A more meaningful parameterization of the Lee–Carter model. Insurance: Mathematics & Economics, 94, 1–8.
4. Dong, Y., Huang, F., Yu, H., & Haberman, S. (2020). Multi-population mortality forecasting using tensor decomposition. Scandinavian Actuarial Journal, 2020/8, 754–775.
5. Gao, G., & Shi, Y. (2021). Age-coherent extensions of the Lee–Carter model. Scandinavian Actuarial Journal, 2021/10, 998–1016.