Forecasting official and parallel exchange rates in the Iraqi economy for the period (2004-2024)
Abstract
The purpose of this study is a comparison between classical approaches and machine learning models in forecasting the parallel and official Iraqi dinar exchange rate. The study utilized the creation of models ARIMA and NNAR on monthly bases for the time span (2004-2024). The exchange rate is an essential mechanism connecting the local economy with the global economic system. Through understanding the pattern of the exchange rate and exploring the variables that assume roles in influencing it, it becomes feasible to design future estimations on its movement, which assists economic units in having appropriate decision-making on how to handle potential risks and dangers. The results indicated that the NNAR model with the neural network surpassed the ARIMA model in accurately forecasting exchange rates, particularly in terms of the auction price. The root mean square error (RMSE) in the NNAR auction model decreased from 14.18 in the ARIMA model to 11.15, and the mean absolute percentage error (MAPE) also dropped from 0.2837 in the ARIMA model to 0.2396
Downloads
References
Ahmadi, M., Jafarzadeh-Ghoushchi, S., Taghizadeh, R., & Sharifi, A. (2019). Presentation of a new hybrid approach for forecasting economic growth using artificial intelligence approaches. Neural Computing and Applications, 31(12), 8661–8680.
Al-Jaf, I. I. (2014). Central Bank Policy and its Effect on Exchange Rate Stability in Iraq (1990–2012) [Master’s thesis, Wasit University].
Al-Mufarji, H. J. (2005). Measuring the Effectiveness of Exchange Rate Determinants in Jordan and the UAE (1991–2002) [Master’s thesis, Karbala University].
Al-Shammari, M. S., & Hamza, H. K. (2015). International Finance: Theoretical Foundations and Analytical Methods. Najaf: Al-Dhiaa Publishing.
Bharadiya, J. P. (2023). Exploring the use of recurrent neural networks for time series forecasting. International Journal of Innovative Science and Research Technology, 8(5), 2023–2027.
Bukhari, L. M. (2010). Foreign Exchange Policy and its Relationship to Monetary Policy. Beirut: Hassan Library.
Butt, S., Ramzan, M., Wong, W.-K., Chohan, M. A., & Bazhair, A. H. (2024). Uncovering the relationship between energy prices and exchange rates in Malaysia: New insights from a nonlinear cointegration perspective. Journal of Economic Studies, 51(2), 134–152.
Chai, T., & Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE). Geoscientific Model Development Discussions, 7(1), 1525–1534.
Darvas, Z., & Schepp, Z. (2025). Forecasting daily GBP/USD exchange rates: A monetary model with rational expectations. Economic Modelling, 126, 103298.
Eichengreen, B. (2008). The Real Exchange Rate and Economic Growth (Working Paper No. 4). Washington, DC: The World Bank.
Eniayewu, P. E., Samuel, G. T., Joshua, J. D., Samuel, B. T., Dogo, B. S., Yusuf, U., Ihekuna, R. O., & Mevweroso, C. R. (2024). Forecasting exchange rate volatility using monetary fundamentals: A MIDAS-GARCH approach. Emerging Markets Finance and Trade, 60(1), 77–96.
Gasta, M. (2024). Forecasting nominal exchange rates using a dynamic model averaging framework. Journal of Forecasting, 43(1), 44–60.
Holmes, M. J., Iregui, A. M., & Otero, J. (2025). Psychological barriers in exchange rates across regimes and foreign exchange market interventions. Journal of International Money and Finance, 134, 102852.
Jabbar, M. (2016). The Effect of Exchange Rate Fluctuations on Financial Markets. Al-Bahith Journal, (16), 15–22.
Jackson, K., & Magkonis, G. (2024). Exchange rate predictability: Fact or fiction? Journal of International Economics, 145, 103677.
Jackson, K., & Magkonis, G. (2024). Exchange rate predictability: Fact or fiction? Journal of International Money and Finance, 142, 103026.
Ma, Y. (2024). Analysis and forecasting of GDP using the ARIMA model. Information Systems and Economics, 5(1), 91–97.
Marghit, A. H. (2019). Money and International Finance (1st ed.). Riyadh: Research and Studies Center.
Naamah, S. F. (2011). The Relationship between Exchange Rates and Interest Rates and their Reflection on the Balance of Payments. Amman: Al-Yazuri Publishing.
Nower, M. (2024). Losing sleep at the international market: Daylight Saving Time and exchange rates. Economics Letters, 241, 111813.
Wada, T. (2022). Out-of-sample exchange rate forecasting: Spectral band regression and LA techniques. Journal of Applied Econometrics, 37(4), 701–718.
Wen, X., Jaxa-Rozen, M., & Trutnevyte, E. (2022). Accuracy indicators for evaluating retrospective performance of energy system models. Applied Energy, 325, 119906.
Xiangmingli. (2004). Trade liberalization and real exchange rate movement. IMF Staff Papers, 51(3), 555–574.
Yang, C. H., Molefyane, T., & Lin, Y. D. (2023). The forecasting of a leading country’s government expenditure using a recurrent neural network with a gated recurrent unit. Mathematics, 11(14), 3085.
Yuan, Y. (2013). Forecasting exchange rate direction using a smooth polynomial support vector machine. Expert Systems with Applications, 40(4), 1200–1211.
Zhu, R., Zhong, G. Y., & Li, J. C. (2024). Forecasting price in a new hybrid neural network model with machine learning. Expert Systems with Applications, 249, 123697.
Published
Deprecated: Return type of Carbon\Traits\Date::createFromTimestamp($timestamp, $tz = null) should either be compatible with DateTime::createFromTimestamp(int|float $timestamp): static, or the #[\ReturnTypeWillChange] attribute should be used to temporarily suppress the notice in /home/iqserver/journals/kjeas.uowasit.edu.iq/lib/pkp/lib/vendor/nesbot/carbon/src/Carbon/Traits/Timestamp.php on line 29
2026-07-09
