Neuroevolution Forecasting of the Living Standards of the Population

DOI

10.2991/ahcs.k.191206.004How to use a DOI?

Keywords

data mining, neuroevolution, genetic algorithm, mutation of activation functions, window method, feature selection method, visualization of neural network topology, living standards of the population

Abstract

The article is devoted to the problem of forecasting indicators of living standards using neuroevolutionary approach. The NEAT method is considered that allows generating the neural network topology automatically. The paper proposes modification of this method and its implementation based on the activation functions mutation, which enabled to expand the set of possible solutions. A comparative analysis of the training, testing, and forecasting accuracy is carried out. Target indicator forecasting was performed with preliminary forecasting of factor signs that increased forecasting accuracy in comparison to the Windows method used to forecast target indicators directly.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Liudmila P. Bilgaeva
AU  - Erzhena Ts. Sadykova
AU  - Victor A. Filippov
PY  - 2019
DA  - 2019/12/12
TI  - Neuroevolution Forecasting of the Living Standards of the Population
BT  - Proceedings of the Fourth Workshop on Computer Modelling in Decision Making (CMDM 2019)
PB  - Atlantis Press
SP  - 18
EP  - 26
SN  - 2589-4900
UR  - https://doi.org/10.2991/ahcs.k.191206.004
DO  - 10.2991/ahcs.k.191206.004
ID  - Bilgaeva2019
ER  -