Forecasting Price Using an Expert System Based on Neural Networks

Authors
Elnaz Ighani Ardebili
Mohammad Mansour Riahi Kashani
Ahmad Aghamohammadi
Abstract
Lack of a structured anticipation about different aspects of high usage product of the national petrochemical company, has forced this company to buy published anticipated prices from foreign countries. Prevent the outflow of foreign exchange and tolerance of political factors, such as sanctions in this field, require a prediction of prices in Iran. Due to chain-like nature of petrochemical products and the absence of precise knowledge of effects of many factors on price, researchers are forced to solve problems with high complexity and high grade of equations. Selecting number and type of input variables of neural network has a significant impact on the performance of a system. Therefore fundamental analysis relying on theory of supply / demand and macroeconomic perspective alongside of Delphi statistical method were used to select the most influential factor. This factor is the price of petroleum products. At First, the overall topology of the neural network is designed using controlled variables, then, considering the independent variables, the optimal network has selected. After creating the user interface, communication of system with optimal neural network was established. To evaluate the actual price of considered product in reference year, it compared with the prices predicted by the proposed system and purchased prices predicted from CMAI; acquired results proved acceptable effectiveness of the proposed system with less than 3% error in predicting of considered chain. Using this system can result in petrochemical companies’ independency from buying forecasted prices from foreign companies and prevent exiting currency from country.
Keywords
Price Forecasting Model
Neural Network
Petrochemical Products
 
[1]       Tiong D. L., Ngo Y. Lee; "Forex trading predication; Artificial Neural Network and Dynamic Time Warping Algorithms"; Proceedings of 4th International Conference on Computing and Informatics, 2013, pp. 92-99.
[2]       Moosmayer D., Chong A., Liu M., Schuppar B.; “A neural network approach to predicting price negotiation outcomes in business-to-business contexts”; Expert Systems with Applications, Vol. 40, 2013, pp. 3028-3035.
[3]       Amusan L., Mosaku T.; "Expert system based predictive cost model for building works: Neural network approch”; International Journal of Basic & Applied Sciences IJBAS-IJENS, Vol. 13:1, 2013, pp. 36-44.
[4]       Wang J. Z., Wang J. J., Zhang Z. G., Guo S. P.; “Forecasting stock indices with Back-Propagation Neural Network”; Expert Systems with Applications, Vol. 38:11, 2012, pp. 346-355.
[5]       Culclasure A.; "Using neural networks to provide local weather forecasts"; Electronic Theses & Dissertations, Georgia Southern University, 2013, p. 32.
[6]       Santhosh S., Shereef I.; ”An efficient weather forecasting system using artificial neural network”; International Journal of Environmental Science and Development, Vol. 1:4, 2012, pp. 321-326.
[7]   فرج‌زاده م.، دارند م. ؛ مقایسه روش‌های رگرسیون خطی و شبکه عصبی مصنوعی در پیش‌بینی میزان مرگ‌ومیر به عنوان تابعی از دمای هوا (مطالعه موردی: تهران)؛ مجله پژوهشی حکیم، دوره 12، شماره سه، 1390، صص 45-53.
[8]   مهرآرا م.، معینی ع.، احراری م.، بهرامی ز.؛ پیش‌بینی قیمت آمونیاک با رویکرد تحلیل‌های بنیادین، تکنیکی و شبکه عصبی؛ فصلنامه اقتصاد مقداری، دوره 6، شماره 1، 1390، صص 51-57.
[9]   فرجام‌نیا ا.، ناصری م.، احمدی م.؛ پیش‌بینی قیمت نفت با شبکه عصبی مصنوعی؛ فصلنامه پژوهش‌های اقتصادی ایران، دوره نهم، شماره 32، 1389، صص 161-196.
[10]  امین ناصری م. ر.، اصفهانیان م.؛ پیش‌بینی کوتاه‌مدت قیمت نفت خام با استفاده از شبکه عصبی پیشخور؛ نشریه بین‌المللی علوم مهندسی دانشگاه علم و صنعت ایران، دوره 1، شماره 19، 1389، صص 27-35.
[11]    Gomez E., Venegas F.; "A review of Artificial Neural Network: How well do they perform in forecasting time series?"; Journal of Statistical Analysis, Vol. 6, No. 2, 2013, pp. 7-15.
[12]    Dunham R.; “The Delphi technique”; www.medsch.wisc.edu/adminmed/2014/, 2014.06.14.
[13]    Chu H., Hwang G.; “A Delphi-based approach to developing expert systems”; Expert Systems with Applications, Vol. 34, No. 4, 2010, pp. 2826-40.
[14]    Smith K., Srivam P.; “Chemical economics handbook”; HIS, 2013.
[15]    http://data.worldbank.org, 2014.07.14.
[16]    Tkacz G.; “Neural network forecasting of Canadian GDP Growth”; International Journal of Forecasting, Vol. 17, 2003, pp.57-69.
[17]    Chi L. Feng. H, Ding L., “Integrating independent component analysis based denoising scheme with neural network for stock price prediction”; Advances in information Sciences and Services-AISS, Vol:4, No. 4, 2012, pp. 27-34.
[18]    Jian Da W.; “An expert system of price forecasting for used cars using adaptive neuro-fuzzy interference”; Expert system with Application, 2011, pp. 7809-7817.
[19]    Wang C. , Lin S., ”Using neural network for forecasting TXO price under different volatility models”, Expert System with Application, Vol. 39, No. 5, 2012, pp. 5025-32.
[20]    Jian W.; “Development of a predictive system for car fuel consumption using an artificial neural network”; Expert System with Application, Vol. 40, No. 5, 2013, pp. 4967-4971.
[21]    Wilson I.D., Ware S.D., Ware J.A.; “Residential property price time series forecasting with neural networks”; Knowledge-Based System, Vol. 15, 2004, pp. 335-346.
[22]    Atiya A. F., El-Shoura S. M., Shaheen S.I.; “A comparison between neural network forecasting techniques”; IEEE Transactions on Neural Networks, Vol. 10, No. 2, 2001, pp. 402-409.
[23]    Zhang G., Patuwo B., Hu M.; “Forecasting with artificial neural networks”; International Journal of Forecasting, Vol. 14, 2000, pp. 35-61.
[24]   Kurkova V., " Kolmogorov's theorem and multilayer neural networks", Neural Networks archive, Vol. 5, No. 3, 1992, pp. 501-506.
Organizational Resources Management Researches
Volume 5, Issue 2
August 2015
Pages 1-20