An economically-oriented neural network approach for optimum estimation of cellular phone subscriptions in noisy and nonlinear markets

Abstract

Cellular phone subscriptions have been increased significantly in recent years through a complex and uncertain pattern. This study estimates the complex and uncertain behavior of cellular subscriptions through an adaptive economically oriented neural network. The superiority of the proposed neural network to fuzzy and conventional regression is shown by comparing mean absolute percentage of error, analysis of variance and Tukey’s test results. Four economic indicators including population, gross domestic production, receipt income per capita and subscriptions of previous year are considered as the input data, and subscriptions to cellular phone service per 100 people is considered as the output data. To show the superiority and applicability of the neural network, the data with respect to the inputs and output have been collected from 51 countries on 5 continents for 15 years (1990–2004). According to the results, in complex and nonlinear markets, the neural network is identified as the preferred model for estimation of numbers of cellular phone subscribers.

Keywords:

• artificial neural network (ANN)
• fuzzy linear regression (FLR)
• cellular phone subscription
• conventional regression (CR)
• complex and noisy markets

Acknowledgment

The authors are grateful for the valuable comments and suggestion from the respected reviewers. Their valuable comments and suggestions have enhanced the strength and significance of our paper. This study was supported by a grant from University of Tehran (Grant No. 8106013/1/14). The authors are grateful for the support provided by the College of Engineering, University of Tehran, Iran.