A New Hybrid Model Using Deep Learning to Forecast Gold Price
Subject Areas : Computer Engineering
1 - Department of Accounting, Azadshahr Branch, Islamic Azad University, Azadshahr, Iran.
Keywords: forecasting, Decomposition, deep learning,
Abstract :
Today, different markets and economic sectors are directly or indirectly affected by gold price; thus its prediction is a big challenge for both investors and researchers. On the other hand, the nonstationary and nonlinear patterns of gold price data cause the prediction process even more complex. To address this challenge, a hybrid model was developed in this paper to predict gold price, with a concentration on enhancing accuracy through considering the gold price data characteristics. To do this, Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) and Gated recurrent units (GRU) were used to deal with the nonstationary and nonlinear nature of the gold price data. The former was first applied to the decomposition of time-series data of gold price into a number of components. Then, GRU was applied to the prediction of the components. To end with, all the components’ prediction results were summed up to attain the final prediction result. The efficiency of the developed model was evaluated using real-world gold data, which confirmed its superiority over the standard methods used for comparison.
[1] J. Białkowski,, M.T. Bohl, , P.M. Stephan, and T.P. Wisniewski, T.P., "The gold price in times of crisis", International Review of Financial Analysis, Vol.41, pp.329-339, 2015.
[2] E. Jianwei, J. Ye, and H. Jin, "A novel hybrid model on the prediction of time series and its application for the gold price analysis and forecasting. Physica A: Statistical Mechanics and its Applications", Vol. 527, p.121454, 2019.
[3] F. Zhou, Z. Huang, and C. Zhang. "Carbon price forecasting based on CEEMDAN and LSTM", Applied energy, Vol. 311, p.1, 2022.
[4] K. Wang, X. Qi, H. Liu, and J. Song," Deep belief network based k-means cluster approach for short-term wind power forecasting", Energy, Vol. 165, pp.840-852, 2018.
[5] P.A. Abken, "The economics of gold price movements", 1980.
[6] J. N. Fortune, "The inflation rate of the price of gold, expected prices and interest rates", Journal of Macroeconomics, Vol. 9, No. 1, pp.71-82, 1987.
[7] G. Grudnitski, and L. Osburn," Forecasting S&P and gold futures prices: An application of neural networks", Journal of Futures Markets, Vol.13, No.6, pp.631-643, 1993.
[8] A. Paris, F. Parisi, and D. Díaz, " Forecasting gold price changes: Rolling and recursive neural network models", Journal of Multinational financial management, Vol.18, No.5, pp.477-487, 2008.
[9] A. Yazdani-Chamzini, S.H. Yakhchali, D. Volungevicˇiene˙, and E. K. Zavadskas. "Forecasting gold price changes by using adaptive network fuzzy inference system", Journal of Business Economics and Management, Vol.13, No.5, pp.994–1010, 2012.
[10] VE. Salis, A. Kumari, A. Singh, " Prediction of gold stock market using hybrid approach. In: Emerging research in electronics", computer science and technology, Springer, pp. 803–812, 2019.
[11] F. Weng, Y. Chen, Z. Wang, M. Hou, J. Luo, and Z. Tian, "Gold price forecasting research based on an improved online extreme learning machine algorithm", Journal of Ambient Intelligence and Humanized Computing, Vol. 11, pp.4101-4111, 2020.
[12] I.E. Livieris, E. Pintelas, and P. Pintelas, " A CNN–LSTM model for gold price time-series forecasting", Neural computing and applications, Vol.32, pp.17351-17360, 2020.
[13] E. Jianwei, J. Ye, and H. Jin, H.," A novel hybrid model on the prediction of time series and its application for the gold price analysis and forecasting", Physica A: Statistical Mechanics and its Applications, Vol. 527, p.121454, 2019.
[14] M. Risse, "Combining wavelet decomposition with machine learning to forecast gold returns", International Journal of Forecasting, Vol.35, No.2, pp.601-615, 2019.
[15] L. Xian, K. He, and K.K.Lai, K.K., "Gold price analysis based on ensemble empirical model decomposition and independent component analysis", Physica A: Statistical Mechanics and its Applications, Vol. 454, pp.11-23, 2016.
[16] Y. Liang, Y. Lin, and Q. Lu, " Forecasting gold price using a novel hybrid model with ICEEMDAN and LSTM-CNN-CBAM", Expert Systems with Applications, Vol.206, pp.117847, 2022.
[17] N.E. Huang, Z. Shen, S. R. Long, M. C. Wu, H.H. Shih, Q. Zheng, N. C. Yen, C.C. Tung, and H.H. Liu, "The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis", Proceedings of the Royal Society of London. Series A: mathematical, physical and engineering sciences, Vol.454, pp.903-995, 1998.
[18] Z.Wu, and N. E. Huang, "Ensemble empirical mode decomposition: a noise-assisted data analysis method. Advances in adaptive data analysis, Vol.1, No.1, pp.1-41,2009.
[19] J.R. Yeh, J.S. Shieh, and N.E. Huang," Complementary ensemble empirical mode decomposition: a novel noise enhanced data analysis method", Adv Adapt Data Anal , Vol.2, pp.135–156, 2010.
[20] X. Li, and C. Li, "Improved CEEMDAN and PSO-SVR modeling for near-infrared noninvasive glucose detection",Computational and mathematical methods in medicine, 2016.
[21] M.E. Torres, M. A. Colominas, G. Schlotthauer, and P. Flandrin, "A complete ensemble empirical mode decomposition with adaptive noise", IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 4144-4147), 2011.
[22] M. A. Colominas, G. Schlotthauer, and M.E.Torres, "Improved complete ensemble EMD: A suitable tool for biomedical signal processing. Biomedical Signal Processing and Control, Vol.14, pp.19-29, 2014.
[23] K. Cho, B. Van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, " Learning phrase representations using RNN encoder-decoder for statistical machine translation.", available online: https://arxiv.org/pdf/1406.1078.pdf, 2014.