Designing and Formulating the Forecasting Model of Economic Growth by Accounting Approach

Abstract

This study examines the explanatory power of accounting information, including operating, investing and financing activities, in forecasting variations in GDP or economic growth. In this approach, GDP has been broken down into four main economic sectors (agriculture, services, oil, and industry and mining) to forecast economic variables. The large number of unknown impact factors, and the presence of non-linear relationships between accounting and economic data have led this study to use multiple combinations of artificial intelligence models of neural networks, genetic algorithms and particle swarm optimization. The results of the models over the years 2006 to 2016 showed that the hybrid model of neural network and particle swarm optimization (HANNPSO) has more accurate forecasting than the hybrid model of neural networks and genetic algorithms (HANNGA). The findings also showed that the effectiveness of operating activities, especially accounting earnings, in forecasting GDP is more than that of financing and investment activities. In addition, the results indicated that among the economic sectors, the relationship between accounting information and the industry and mining sector is considerably high. The main consequence of this study is the existence of effective link between accounting and economic information that must be included in the economic and financial decisions.

Keywords

• gross domestic product
• accounting
• economic
• artificial intelligence models