Sains Malaysiana 52(11)(2023): 3293-3306

http://doi.org/10.17576/jsm-2023-5211-20

 

A Hybrid Approach for Accurate Forecasting of Exchange Rate Prices using VMD-CEEMDAN-GRU-ATCN Model

(Pendekatan Hibrid untuk Ramalan Tepat Harga Kadar Pertukaran menggunakan Model VMD-CEEMDAN-GRU-ATCN)

 

REHAN KAUSAR1, FARHAT IQBAL2,3,*, ABDUL RAZIQ2 & NAVEED SHEIKH4

 

1Department of Statistics, Sardar Bahadur Khan Women’s University, Quetta, Pakistan

2Department of Statistics, University of Balochistan, Quetta, Pakistan

3Department of Mathematics, Imam Abdulrahman Bin Faisal University, Saudi Arabia

4Department of Mathematics, University of Balochistan, Quetta, Pakistan

 

Diserahkan: 5 Mei 2023/Diterima: 23 Oktober 2023

 

Abstract

The foreign exchange (Forex) market has greatly influenced the global financial market. While Forex trading offers investors substantial yield prospects, some risks are also involved. It is challenging to accurately model financial time series due to their nonlinear, non-stationary and noisy properties with an uncertain and hidden relationship. Thus, developing extremely precise forecasting techniques is crucial for investors and decision-makers. This study introduces a novel hybrid forecasting model, VMD-CEEMDAN-GRU-ATCN, designed to improve Forex price prediction accuracy. To begin with, our proposed model utilizes the variational model decomposition (VMD) technique for breaking down raw prices into multiple sub-components and residual terms. The complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) technique is utilized to extract features from the residual terms, which involves further decomposition and analysis of these complex information-containing terms. These sub-components are then predicted by the gated recurrent unit (GRU) model. To enhance the effectiveness of our hybrid model, we include the open, high, low, and close prices and seven Forex market technical indicators. Finally, an attention-based temporal convolutional network (ATCN) model is used to obtain the Forex price forecasts. For both one-step and multi-step ahead forecasting, our proposed VMD-CEEMDAN-GRU-ATCN model has demonstrated superior and consistent performance in predicting USD/PKR exchange rate price series.

 

Keywords: Attention mechanism; Forex; dual decomposition strategy; hybrid deep learning models; temporal convolutional network

Abstrak

Pasaran pertukaran asing (Forex) telah banyak mempengaruhi pasaran kewangan global. Walaupun perdagangan Forex menawarkan prospek hasil yang besar kepada pelabur, beberapa risiko turut terlibat. Adalah mencabar untuk memodelkan siri masa kewangan dengan tepat kerana sifatnya yang tidak linear, tidak pegun dan hingar dengan hubungan yang tidak pasti dan tersembunyi. Oleh itu, membangunkan teknik ramalan yang sangat tepat adalah penting untuk pelabur dan pembuat keputusan. Kajian ini memperkenalkan model ramalan hibrid baru, VMD-CEEMDAN-GRU-ATCN yang direka untuk meningkatkan ketepatan ramalan harga Forex. Sebagai permulaan, model cadangan kami menggunakan teknik penguraian model variasi (VMD) untuk memecahkan harga mentah kepada terma berbilang sub-komponen dan sisa. Teknik penguraian mod empirik ensembel lengkap dengan hingar suai (CEEMDAN) digunakan untuk mengekstrak ciri daripada terma sisa yang melibatkan penguraian dan analisis lanjut bagi terma yang mengandungi maklumat yang kompleks ini. Sub-komponen ini kemudiannya diramalkan oleh model unit berulang berpagar (GRU). Untuk meningkatkan keberkesanan model hibrid ini, kami memasukkan harga terbuka, tinggi, rendah dan tertutup serta tujuh penunjuk teknikal pasaran Forex. Akhir sekali, model rangkaian konvolusi temporal berasaskan perhatian (ATCN) digunakan untuk mendapatkan ramalan harga Forex. Untuk ramalan selangkah dan berbilang langkah ke hadapan, model cadangan VMD-CEEMDAN-GRU-ATCN telah menunjukkan prestasi unggul dan tekal dalam meramalkan siri harga pertukaran USD/PKR.

 

Kata kunci: Forex; model pembelajaran mendalam hibrid; strategi penguraian dual; mekanisme perhatian; rangkaian konvolusi temporal

 

RUJUKAN

Aryal, S., Nadarajah, D., Kasthurirathna, D., Rupasinghe, L. & Jayawardena, C. 2019. Comparative analysis of the application of Deep Learning techniques for Forex Rate prediction. International Conference on Advancements in Computing (ICAC). pp. 329-333. https://doi.org/10.1109/ICAC49085.2019.9103428

Bai, S., Kolter, J.Z. & Koltun, V. 2018. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. ArXiv Preprint ArXiv: 1803.01271.

            https://doi.org/10.48550/arXiv.1803.01271

Cheng, W., Wang, Y., Peng, Z., Ren, X., Shuai, Y., Zang, S., Liu, H., Cheng, H. & Wu, J. 2021. High-efficiency chaotic time series prediction based on time convolution neural network. Chaos, Solitons & Fractals 152: 111304. https://doi.org/10.1016/j.chaos.2021.111304

Cao, J., Li, Z. & Li, J. 2019. Financial time series forecasting model based on CEEMDAN and LSTM. Physica A: Statistical Mechanics and its Applications 519: 127-139. https://doi.org/10.1016/j.physa.2018.11.061

Das, S.R., Mishra, D. & Rout, M. 2019. A hybridized ELM using self-adaptive multi-population-based Jaya algorithm for currency exchange prediction: An empirical assessment. Neural Computing and Applications 31(11): 7071-7094. https://doi.org/10.1007/s00521-018-3552-8

Deng, T., He, X. & Zeng, Z. 2018. Recurrent neural network for combined economic and emission dispatch. Applied Intelligence 48: 2180-2198. https://doi.org/10.1007/s10489-017-1072-3

Diebold, F.X. & Mariano, R.S. 2002. Comparing predictive accuracy. Journal of Business & Economic Statistics 20(1): 134-144. https://doi.org/10.1198/073500102753410444

Dragomiretskiy, K. & Zosso, D. 2013. Variational mode decomposition. IEEE Transactions on Signal Processing 62(3): 531-544. https://doi.org10.1109/TSP.2013.2288675

Fan, J., Zhang, K., Zhu, Y. & Chen, B. 2021. Parallel spatio-temporal attention-based TCN for multivariate time series prediction. Neural Computing and Applications 35: 13109-13118. https://doi.org/10.1007/s00521-021-05958-z

Guo, H., Zhang, D., Liu, S., Wang, L. & Ding, Y. 2021. Bitcoin price forecasting: A perspective of underlying blockchain transactions. Decision Support Systems 151: 113650. https://doi.org/10.1016/j.dss.2021.113650

Hu, Z., Zhao, Y. & Khushi, M. 2021. A survey of Forex and stock price prediction using deep learning. Applied System Innovation 4(1): 9. https://doi.org/10.3390/asi4010009 

Hua, Y. & Zehao, C. 2020. Short-term traffic flow prediction based on temporal convolutional networks. Journal of South China University of Technology (Natural Science Edition) 48: 8. https://doi.org/10.1109/ITSC48978.2021.9564803

Jun, W., Lingyu, T., Yuyan, L. & Peng, G. 2017. A weighted EMD-based prediction model  based on TOPSIS and feed forward neural network for noised timeseriesKnowledge-Based Systems 132: 167-178. https://doi.org/10.1016/j.knosys.2017.06.022

Karevan, Z. & Suykens, J.A.K. 2020. Transductive LSTM for time-series prediction: An application to weather forecasting. Neural Networks 125: 1-9. https://doi.org/10.1016/j.neunet.2019.12.030

Long, J., Shelhamer, E. & Darrell, T. 2015. Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3431-3440. https://doi.org/10.1109/CVPR.2015.7298965

Loureiro, A.L., Miguéis, V.L. & da Silva, L.F. 2018. Exploring the use of deep neural networks for sales forecasting in fashion retail. Decision Support Systems 114: 81-93. https://doi.org/10.1016/j.dss.2018.08.010

Peng, Z., Peng, S., Fu, L., Lu, B., Tang, J., Wang, K. & Li, W. 2020. A novel deep learning ensemble model with data denoising for short-term wind speed forecasting. Energy Conversion and Management 207: 112524. https://doi.org/10.1016/j.enconman.2019.112524

Torres, M.E., Colominas, M.A., Schlotthauer, G. & Flandrin, P. 2011. A complete ensemble empirical mode decomposition with adaptive noise. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 4144-4147.  https://doi.org/10.1109/ICASSP.2011.5947265

Ulina, M., Purba, R. & Halim, A. 2020. Foreign exchange prediction using CEEMDAN and improved FA-LSTM. Fifth International Conference on Informatics and Computing (ICIC). pp. 1-6. https://doi.org/10.1109/ICIC50835.2020.9288615

Wei, Y., Sun, S., Ma, J., Wang, S. & Lai, K.K. 2019. A decomposition clustering ensemble learning approach for forecasting foreign exchange rates. Journal of Management Science and Engineering 4(1): 45-54. https://doi.org/10.1016/j.jmse.2019.02.001

Yang, W., Wang, J., Niu, T. & Du, P. 2019. A hybrid forecasting system based on a dual decomposition strategy and multi-objective optimization for electricity price forecasting. Applied Energy 235: 1205-1225. https://doi.org/10.1016/j.apenergy.2018.11.034

Yasir, M., Durrani, M.Y., Afzal, S., Maqsood, M., Aadil, F., Mehmood, I. & Rho, S. 2019. An intelligent event-sentiment-based daily foreign exchange rate forecasting system. Applied Sciences 9(15): 2980. https://doi.org/10.3390/app9152980

 Yildirim, D.C., Toroslu, I.H. & Fiore, U. 2021. Forecasting directional movement of Forex data using LSTM with technical and macroeconomic indicators. Financial Innovation 7(1): 1-36. https://doi.org/10.1186/s40854-020-00220-2

Yujia, Z., Zhicheng, D., Songwei, G. & Jirong, W. 2020. Dynamic personalized search based on RNN with attention mechanism. Chinese Journal of Computers 43: 812-826.  https://doi.org/10.11897/SP.J.1016.2020.00812

Zhang, C., Pan, H., Ma, Y. & Huang, X. 2019. Analysis of Asia Pacific stock markets with a novel multiscale model. Physica A: Statistical Mechanics and its Applications 534: 120939. https://doi.org/10.1016/j.physa.2019.04.175

Zhang, T., Tang, Z., Wu, J., Du, X. & Chen, K. 2021. Multi-step-ahead crude oil price forecasting based on two-layer decomposition technique and extreme learning machine optimized by the particle swarm optimization algorithm. Energy 229: 120797. https://doi.org/10.1016/j.energy.2021.120797

Zhen, Y., Fang, J., Zhao, X., Ge, J. & Xiao, Y. 2022. Temporal convolution network based on attention mechanism for well production prediction. Journal of Petroleum Science and Engineering 218: 111043. https://doi.org/10.1016/j.petrol.2022.111043

Zhou, J. & Wang, S. 2021. A carbon price prediction model based on the secondary decomposition algorithm and influencing factors. Energies 14(5): 1328.  https://doi.org/10.3390/en14051328

 

*Pengarang untuk surat-menyurat; email: Farhat.iqbal@um.uob.edu.pk

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

   

sebelumnya