Perceptron Model of Forecasting Life Exapectancy via Insurance Lee-Carter Mortality Function*

Andreeski, Cvetko and Dimirovski, Georgi (2018) Perceptron Model of Forecasting Life Exapectancy via Insurance Lee-Carter Mortality Function*. In: IEEE Systems men and cybernetics, 8-10 October, Miyazaki Japonija.

Full text not available from this repository.

Abstract

Abstract— Forecasting of mortality function is important for many fields of human work like insurance companies,
government projections of the human assets, and medical
research. During past years many models were presented. The widely adopted Lee-Carter model is based on the log function on mortality rate which includes as input variables quantities of age, year of mortality function and bias, which also enables predicting the life expectancy. In this paper a perceptron based model with
minimum number of nodes in the network having custom
transfer function is proposed. Results are compared with those of standard Lee-Carter and other neural network based models by using MSE type of error. This model is simpler than other neural networks and is easier to handle adjusting the weights while computing results are rather comparable with those of more complex neural network models.
Keywords— ANN based models; forecasting; improved LeeCarter model; insurance policy; life expectancy; mortality function

Item Type: Conference or Workshop Item (Paper)
Subjects: Scientific Fields (Frascati) > Engineering and Technology > Other engineering and technologies
Divisions: Faculty of Tourism and Hospitality
Depositing User: Mr Bojan Sekulovski
Date Deposited: 16 Oct 2018 09:36
Last Modified: 16 Oct 2018 09:36
URI: https://eprints.uklo.edu.mk/id/eprint/1367

Actions (login required)

View Item View Item