forecasting of polyethylene terephthalate' chain price ,using system based on neural networks

the lack of a structured anticipating about high usage product of the national petrochemical company, has forced this company to buy forecasted price from foreign countries. prevent the outflow of foreign exchange and tolerance of political factors such as sanctions in this field requires a forecast of prices in our country. due to the chain-like nature of the petrochemical products, and the absence of precise knowledge of the effects of many factors affecting the price, researchers are forced to solve problems with high complexity and high grade equations. selecting the number and the type of input variables of neural network is a significant impact on the performance of system, so, fundamental analysis, relying on the theory of supply and demand and macroeconomic perspective, and delphi statistical method are used to select the most influential factor is the price of petroleum products. first, the overall topology of the neural network is designed, using the controlled variables, then, considering the independent variables, the optimal network selected. after creating the user interface, communication of system with optimal neural network was established. to evaluating, the actual price of the considered product in reference year, compared with the prices predicted by the proposed system and purchased predicted prices from cmai; and the results proved the acceptable effectiveness of the proposed system with less than 3% error in predicting of considered chain. providing this system can make petrochemical companies independent from buying forecasted prices from foreign companies and can force from exiting the currency from country.