Table of Content

Open AccessOpen Access


Application of Radial Basis Function Networks with Feature Selection for GDP Per Capita Estimation Based on Academic Parameters

Abdullah Erdal Tümer1,∗, Aytekin Akku¸s2

1 Necmettin Erbakan University, Department of Computer Engineering, Campus of Köyce˘giz, 42140, Konya, Turkey
2 Necmettin Erbakan University Department of Industrial Engineering, Institute Of Science, Campus of Köyce˘giz, 42140, Konya, Turkey

* Corresponding Author: E-mail:

Computer Systems Science and Engineering 2019, 34(3), 145-150.


In this work, a system based on Radial Basis Function Network was developed to estimate Gross Domestic Product per capita. The data set based on 180 academic parameters of 13 Organisation for Economic Co-operation and Development countries was used to verify the effectiveness and accuracy of the proposed method. Gross Domestic Product per capita was studied to be estimated for the first time with academic parameters in this study. The system has been optimized using feature selection method to eliminate unimportant features. Radial Basis Function network results and Radial Basis Function network with feature selection method results were compared. The findings show that the Radial Basis Function network with feature selection is 10% more successful than the Radial Basis Function results. Based on results, this methodology can be applied in applications of Gross Domestic Product per capita forecasting.


Cite This Article

A. Erdal Tümer and A. Akku¸s, "Application of radial basis function networks with feature selection for gdp per capita estimation based on academic parameters," Computer Systems Science and Engineering, vol. 34, no.3, pp. 145–150, 2019.


This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 1310


  • 1346


  • 1


Share Link