A hybrid computational intelligence model for foreign exchange rate forecasting
محورهای موضوعی : Mathematical OptimizationM Khashei 1 , F Mokhatab Rafiei 2 , M Bijari 3 , S.R Hejazi 4
1 - Ph.D. Student, Dept. of Industrial Engineering, Isfahan University of Technology, Isfahan, Iran
2 - Assistant Professor, Dept. of Industrial Engineering, Isfahan University of Technology, Isfahan, Iran
3 - Associate Professor, Dept. of Industrial Engineering, Isfahan University of Technology, Isfahan, Iran
4 - Associate Professor, Dept. of Industrial Engineering, Isfahan University of Technology, Isfahan, Iran
کلید واژه: fuzzy logic, Financial Markets, Computational Intelligence, Artificial Neural Networks (ANNs), Time series forecasting, exchange rate,
چکیده مقاله :
Computational intelligence approaches have gradually established themselves as a popular tool for forecasting the complicated financial markets. Forecasting accuracy is one of the most important features of forecasting models; hence, never has research directed at improving upon the effectiveness of time series models stopped. Nowadays, despite the numerous time series forecasting models proposed in several past decades, it is widely recognized that exchange rates are extremely difficult to forecast. Artificial Neural Networks (ANNs) are one of the most accurate and widely used forecasting models that have been successfully applied for exchange rate forecasting. In this paper, a hybrid model is proposed based on the basic concepts of artificial neural networks in order to yield more accurate results than the traditional ANNs in short span of time situations. Three exchange rate data sets—the British pound, the United States dollar, and the Euro against the Iran rial-are used in order to demonstrate the appropriateness and effectiveness of the proposed model. Empirical results of exchange rate forecasting indicate that hybrid model is generally better than artificial neural networks and other models presented for exchange rate forecasting, in cases where inadequate historical data are available. Therefore, our proposed model can be a suitable alternative model for financial markets to achieve greater forecasting accuracy, especially in incomplete data situations.
