Anticipation of Macroeconomic Variables Impact on Stock Prices Using Artificial Neural Network with GMDH Algorithm

The economy of every country is composed of different parts, the relationship among which determines the economics direction of that country. The capital market together with money market make up the financial market as the fundamental basics of an economy. Their operation has significant influence on the growth and development of the economy. In cases where there is no constructive relationship between the financial market and other parts of the economy, economic performance might be subject to distortions. The stock market as a fundamental basic of the financial market has a crucial role in facilitation of investments in the capital market. Given the importance of expectations in different economic fields, the main purpose of this study is to project behavior of the Tehran stock exchange price index. Therefore, after a review of dominant economic theories, we use a new method, artificial neural network GMDH, to forecast the impact of macroeconomic variable on the Tehran stock exchange price index. The GMDH Algorithm is a nonlinear model to anticipate complex systematic relationships between variables of the model. The special feature of this deductive algorithm is recognition and screening of the most effective variable to estimate the model with training samples and omit the non-significant ones from the simulation process with testing samples. So, we can solve the model via iterative methods to minimize the typical standard Error like RMSE, MAPE, and so on.