Comparison of GRU and CNN Methods for Predicting the Exchange Rate of Argentine Peso (ARS) against US Dollar (USD)
(1) * Facundo Agustin Mail (University of Mendoza, Argentina)
(2) Patricia De Melin Mail (University of Mendoza, Argentina)
*corresponding author

Abstract


This study aims to compare the performance of the Gated Recurrent Unit (GRU) and Convolutional Neural Network (CNN) methods in predicting the exchange rate of the Argentine Peso (ARS) against the United States Dollar (USD). Using historical exchange rate data from January 2017 to December 2022, both models were trained and evaluated using Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R² Score metrics. The results showed that the GRU model outperformed the CNN model in all evaluation metrics with MSE of 1.907 compared to 3.273 for CNN, RMSE of 1.381 compared to 1.809 for CNN, MAE of 1.063 compared to 1.433 for CNN, and R² Score of 0.996 compared to 0.994 for CNN. This study shows that GRU is more effective in capturing temporal patterns in currency exchange rate data compared to CNN, which highlights the advantages of recurrent architecture for financial time series prediction problems.

   

DOI

https://doi.org/10.33292/ijarlit.v2i1.31 		      

Article metrics

10.33292/ijarlit.v2i1.31 Abstract views : 151 | PDF views : 95

   

Cite

How to cite item
   

Full Text

Download

References


R. Meese and K. S. Rogoff, The out-of-sample failure of empirical exchange rate models: sampling error or misspecification? Board of Governors of the Federal Reserve System, 1982.

S. Galeshchuk, "Neural networks performance in exchange rate prediction," Neurocomputing, vol. 172, pp. 446-452, 2016.

S. Siami-Namini, N. Tavakoli, and A. S. Namin, "A comparison of ARIMA and LSTM in forecasting time series," in 2018 17th IEEE international conference on machine learning and applications (ICMLA), 2018, pp. 1394-1401.

T. Fischer and C. Krauss, "Deep learning with long short-term memory networks for financial market predictions," Eur. J. Oper. Res., vol. 270, no. 2, pp. 654-669, 2018.

K. Cho et al., "Learning phrase representations using RNN encoder-decoder for statistical machine translation," arXiv Prepr. arXiv1406.1078, 2014.

A. Borovykh, S. Bohte, and C. W. Oosterlee, "Conditional time series forecasting with convolutional neural networks," arXiv Prepr. arXiv1703.04691., 2017.

T.-T. Nguyen and S. Yoon, "A Novel Approach to Short-Term Stock Price Movement Prediction Using Transfer Learning," Appl. Opt. Sci., vol. 9, no. 22, p. 4745, 2019, doi: 10.3390/app9224745.

J. Wang, X. Li, H. Jia, T. Peng, and J. Tan, "Predicting Stock Market Volatility From Candlestick Charts: A Multiple Attention Mechanism Graph Neural Network Approach," Math. Probl. Eng., vol. 2022, pp. 1-16, 2022, doi: 10.1155/2022/4743643.

J. M. Wu, Z. Li, G. Srivastava, M. Tasi, and J. C. Lin, "A Graph-based Convolutional Neural Network Stock Price Prediction With Leading Indicators," Softw. Pract. Exp., vol. 51, no. 3, pp. 628-644, 2020, doi: 10.1002/spe.2915.

C. Yang, J. Zhai, and G. Tao, "Deep Learning for Price Movement Prediction Using Convolutional Neural Network and Long Short-Term Memory," Math. Probl. Eng., vol. 2020, pp. 1-13, 2020, doi: 10.1155/2020/2746845.

H. Wang, J. Wang, L. Cao, Y. Li, Q. Sun, and J. Wang, "A Stock Closing Price Prediction Model Based on CNN-BiSLSTM," Complexity, vol. 2021, no. 1, 2021, doi: 10.1155/2021/5360828.

J. E. Choi and D. W. Shin, "The Roles of Differencing and Dimension Reduction in Machine Learning Forecasting of Employment Level Using the FRED Big Data," Commun. Stat. Appl. Methods, vol. 26, no. 5, pp. 497-506, 2019, doi: 10.29220/csam.2019.26.5.497.

Z. Bao, Q. Wei, Q. Wei, T. Zhou, X. Jiang, and T. Watanabe, "Predicting stock high price using forecast error with recurrent neural network," vol. 6, no. 1, pp. 283-292, 2021, doi: 10.2478/AMNS.2021.2.00009.

A. Lawi, H. Mesra, and S. B. H. Amir, "Implementation of Long Short-Term Memory and Gated Recurrent Units on grouped time-series data to predict stock prices accurately," J. Big Data, vol. 9, no. 1, 2022, doi: 10.1186/s40537-022-00597-0.

B. Qian et al., "Dynamic Multi-Scale Convolutional Neural Network for Time Series Classification," Ieee Access, vol. 8, pp. 109732-109746, 2020, doi: 10.1109/access.2020.3002095.

S. Di, C. Gallicchio, and A. Micheli, "On the Effectiveness of Gated Echo State Networks for Data Exhibiting Long-Term Dependencies," Comput. Sci. Inf. Syst., vol. 19, no. 1, pp. 379-396, 2022, doi: 10.2298/csis210218063d.

L. Kilian and M. P. Taylor, "Why is it so difficult to beat the random walk forecast of exchange rates?", J. Int. Econ., vol. 60, no. 1, pp. 85-107, 2003.

S. Galeshchuk and S. Mukherjee, "Deep networks for predicting direction of change in foreign exchange rates," Intell. Syst. Accounting, Financ. Manag., vol. 24, no. 4, pp. 100-110, 2017.

I. E. Livieris, E. Pintelas, and P. Pintelas, "A CNN-LSTM model for gold price time-series forecasting," Neural Comput. Appl., vol. 32, pp. 17351-17360, 2020.

B. Lim and S. Zohren, "Time-series forecasting with deep learning: a survey," Philos. Trans. R. Soc. A, vol. 379, no. 2194, p. 20200209, 2021.


Refbacks

  • There are currently no refbacks.


View My Stats IJARLIT