Analyzing economic structure and comparing the results of the predicted economic growth based on linear and non-linear models

摘要

Investigating the effectivefactors on economic growth is of great importance for most economists. Although, lots of studies have been done on economic growth in the world, it has less been regarded in Iran. In this article, by estimating growth regression, we attempt to investigate the supply side of economic growth in Iran. Then a comparison was done between the predictive results of Neural network (NN) and Slow models. Also by comparing the predictive results of models for the average percentage of annual growth, it is predicted that the average percentage of solow and neural-network models are 7.17 and 5.92% for 2002 to 2006, respectively. Evaluation of results from the models on the basis of criteria shows that Neural-networkmodelpredicts better than Solow model. In other words, forecasting by the model neural-network is recommended.