Title: Improved prediction of household expenditure by living standard measures via a unique neural network: the case of Iran

Authors: Ali Azadeh; Samaneh Davarzani; Azadeh Arjmand; Mansoureh Khakestani

Addresses: School of Industrial Engineering, College of Engineering, University of Tehran, P.O. Box: 11365-4563, Enghelab Ave. Tehran, Iran ' School of Industrial Engineering, College of Engineering, University of Tehran, P.O. Box: 11365-4563, Enghelab Ave. Tehran, Iran ' Department of Industrial Engineering, College of Engineering, Al Zahra University, Tehran, Iran ' Department of Industrial Engineering, College of Engineering, University of Bojnourd, Iran

Abstract: There is a growing interest in predicting of household expenditure and poverty measures by combining detailed information from a household budget survey. But very few researchers have gathered information on household incomes or consumption expenditures in developing countries. The objective of this work is to analyse the relationship between household expenditure, income and living standard measures (LSM). To achieve this, models of household expenditure were developed using the data available in the Statistical Center of Iran. A unique neural network is developed to forecast and estimate household expenditures. Four different model including linear regression, quadratic regression, cubic regression and genetic algorithm are developed in order to forecast LSM. The superiority of the proposed ANN in comparison with the stated approaches is shown numerically. This is the first study that utilises an intelligent network model to improve the prediction of household expenditure.

Keywords: household expenditure; living standards measures; LSM; regression models; artificial neural networks; ANNs; genetic algorithms; Iran; poverty measures; developing countries.

DOI: 10.1504/IJPQM.2016.074464

International Journal of Productivity and Quality Management, 2016 Vol.17 No.2, pp.142 - 182

Available online: 27 Dec 2015 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article