Analysis of economic structure and comparing the results of the predicted economic growth, on the base of Solow, Fuzzy-logic and Neural-Fuzzy models

Investigating the effective factors which effect economic growth is important for most economists. Although lots of studies have been done on economic growth in the world, it gets little attentions in Iran. In this article, by estimating growth regression, we try to investigate the supply side economic growth of Iran. Then we compare the predictive results of Fuzzy-logic, Neural-Fuzzy and solow models. The results show that there had been negative significant relationship (i.e. -0.035) between unstable policy and economic growth rate in Iran during investigated periods, i. e. (1959 to 2001). In this model, the effect of the used expenses of the government is positive i.e. 0.01. Furthermore, the estimated results of long time relationship show that the variable coefficient of capital is about: 0.319, the variable coefficient of labor power is about 0.016, the variable coefficient of exportation is about 0.001 and the variable coefficient of inflation is about -0.001. And also by comparing the predictive results of models for thee average annual growth, it is predicted that (7.17 percent) in Solow model, (5.92 percent) in Neural-Fuzzy model and (6.46 percent) in Fuzzy-logic model in the related periods i.e. 2002-2006. And by comparing criteria it has been determined that, model Neural-Fuzzy predicts better than Fuzzy-logic and Solow models. In other words, forecasting by the model Neural-Fuzzy is recommended.

کلیدواژه ها:

Fuzzy Neural Network (FNN) ، Fuzzy-Logic ، Solow model ، economic growth ، forecasting growth ، economic structure ، supply side economics ، economical factors