Comparison of The Performance of Artificial Neural Network Models for Exchange Rate Prediction in Iran

Hashemi Dizaj, Abdul Rahim; Haziri Nairi, Hatef; Poorvahdani, Rasool

doi:10.22096/esp.2020.43397

Comparison of The Performance of Artificial Neural Network Models for Exchange Rate Prediction in Iran

Document Type : Original Article

Authors

Abdul Rahim Hashemi Dizaj ¹

Hatef Haziri Nairi ¹

Rasool Poorvahdani ²

¹ Assistant Professor, Faculty of Social Sciences, Mohaghegh Ardabili University, Ardabil, Iran.

² Master of Management, Faculty of Social Sciences, Mohaghegh Ardabili University, Ardabil, Iran.

10.22096/esp.2020.43397

Abstract

Given the high exchange rate fluctuations in Iran, its prediction is one of the major issues and challenges for different groups in the country. This study investigates the performance of six different static and dynamic neural networks for forecasting exchange rates using fundamental, technical and hybrid approaches and using seasonal data over the period (1) 2004- (4) 1396 for variables influencing exchange rate including inflation, Liquidity and GDP for the two countries, Iran and the United States. The findings show that the number of neurons did not have a regular effect on the performance of the networks and that the best results occurred at breaks of three and four. The results also show that the best performance of the static neural network is achieved by a technical approach with a structure of sixteen neurons and four interruptions which provides a relatively accurate exchange rate prediction despite the low number of input data.

Keywords

Time Series

Currency Forecasting

Artificial Neural Network

Artificial Intelligence

Ebrahimi, Maryam (2013), Exchange Rate Prediction Using Neural Network with Two Technical and Fundamental Approaches, M.Sc. Thesis in Economic Development, Al-Zahra University, Tehran .
Ebrahimi, Maryam and Mehdi Pedram (2014), "Study of the importance and impact of economic variables on the exchange rate in Iran", Al-Zahra University Economic Development Policy Quarterly, Second Year, No. 3, pp. 141-168.
Ehsanifar, Mohammad and Reza Ehteshamaraei (2015), "Forecasting the exchange rate in the capital market using the accumulated moving average self-regression models and neural network" (Case study: Australian dollar, Canadian dollar, Japanese Yen and British Pound), Quarterly Journal of Securities Finance, Volume 8, Number 27, pp. 35-51.
Ahmadi Amaleh, Elham (2013), The use of artificial intelligence for technical analysis of the stock market based on Japanese candlestick chart patterns, M.Sc. Thesis in Industrial Engineering, Yazd University, Yazd.
Asghari Oskooi, Mohammad Reza (2002), "Application of neural networks in predicting time series", Iranian Economic Research Quarterly, Fourth Year, No. 12, pp. 69-96.
Bahrampour, Peyman and Nikbakhsh Javadian (2014), "Daily Forecast of Pound / Dollar Exchange Rate in Forex Market Using Neural Network", International Journal of Industrial Engineering and Production Management, Volume 25, Number 4, pp. 377-388.
Jalaei Esfandabadi, Seyed Abdolmajid; Hosseini, Seyed Jafar and Hossein Nezamabadipour (2012), "Study of monetary exchange rate fluctuations and its prediction with neural networks in Iran", Macroeconomics Research, Year 7, No. 14, pp. 35- 60.
Hanafizadeh, Payam and Abolfazl Jafari (2010), "Combined model of artificial and self-organizing artificial neural networks for stock price forecasting", Quarterly Journal of Industrial Management Studies, Year 8, No. 19, pp. 165-187.
Khashei, Mehdi and Mehdi Bijari (2008), "Improving the performance of financial forecasts with linear and nonlinear combination of accumulated moving average self-regression and artificial neural networks", Quarterly Journal of Economic Research, Year 8, No. 2, pp. 83-100.
Rai, Reza and Meysam Mahmoudia Azar (2014), "Predicting the future return of the stock market using Arima models, neural network and wavelet noise reduction", Quarterly Journal of Asset Management and Financing, Second Year, No. 2 (consecutive 5), pp. 1-16.
Rostamzadeh, Mehdi (2011), Evaluation of Value Determination Models Using Genetic Algorithms (Case Study of Iran and the European Union), PhD Thesis, Mazandaran University, Mazandaran.
زراء‌نژاد ، منصور; Fiqh Majidi, Ali and Ruhollah Rezaei (2008), "Exchange Rate Prediction Using Artificial Neural Networks and ARIMA Model", Quantitative Economics Quarterly (Former Economic Studies), Fifth Year, No. 4, pp. 107-130.
Salvatore, Dominic (1396), International Finance, translated by Hamid Reza Arbab, Volume 2, sixth edition, Tehran: Nashr-e Ney.
Sharif Moghadam, Shafaq and Seyed Zabihollah Hashemi (1397), "Predicting the exchange rate of Euro to Dollar with artificial neural network technique", Financial Engineering and Securities Management, Year 9, No. 37, pp. 399-413.
Taybi, Seyed Kamil; Movahednia, Nasser and Masoumeh Kazemini (2008), "Using Neural Networks in Predicting Economic Variables and Comparing It with Econometric Methods: Predicting Exchange Rate Trends in Iran", Sharif Scientific Research Journal, Twenty-fourth year, No. 43, pp. 99-104.
Ghaffari, Mehdi and Raheleh Yousefi (2011), "Currency Price Forecast Modeling Using Neural Networks", Journal of Financial Engineering and Securities Management, Year 2, No. 8, pp. 99-119.
Kia, Seyed Mostafa (1397), Neural Networks in MATLAB, sixth edition, Tehran: Kian University Press.
Minhaj, Mohammad Baqer (1397), Basics of Neural Networks, Volume 1, Twelfth Edition, Tehran: Amir Kabir University of Technology Press (Tehran Polytechnic).
Mousavian, Seyed Mehdi (2012), Combining artificial neural network model with magnetic algorithm in order to predict the exchange rate and compare it with ARIMA and GARCH time series models, M.Sc. Thesis Of Economic Sciences, Allameh-Tabatabai University, Tehran.