Latin American market asset volatility analysis: a comparison of garch model, artificial neural networks and support vector regression

• Autorzy: Chung Víctor , Espinoza Jenny

Identyfikatory

DOI

10.35784/acs-2023-21

• Języki publikacji: EN

Abstrakty

EN

The objective of this research was to compare the effectiveness of the GARCH method with machine learning techniques in predicting asset volatility in the main Latin American markets. The daily squared return was utilized as a volatility indicator, and the accuracy of the predictions was assessed using root mean square error (RMSE) and mean absolute error (MAE) metrics. The findings consistently demonstrated that the linear SVR-GARCH models outperformed other approaches, exhibiting the lowest MAE and MSE values across various assets in the test sample. Specifically, the SVR-GARCH RBF model achieved the most accurate results for the IPC asset. It was observed that GARCH models tended to produce higher volatility forecasts during periods of heightened volatility due to their responsiveness to significant past changes. Consequently, this led to larger squared prediction errors for GARCH models compared to SVR models. This suggests that incorporating machine learning techniques can provide improved volatility forecasting capabilities compared to the traditional GARCH models.

Słowa kluczowe

EN

return; volatility; GARCH; Machine Learning

• Wydawca: Polskie Towarzystwo Promocji Wiedzy ; Lublin University of Technology
• Czasopismo: Applied Computer Science
• Rocznik: 2023
• Tom: Vol. 19, no 3
• Strony: 1--16
• Opis fizyczny: Bibliogr. 29, fig., tab.

Twórcy

autor

Chung Víctor

• Universidad Nacional Pedro Ruiz Gallo, FACFyM, Perú

• https://orcid.org/0000-0002-8358-3939

autor

Espinoza Jenny

• Universidad Tecnológica del Perú, Perú

• https://orcid.org/0000-0002-3761-0721

Bibliografia

• [1] Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity. Journal of Econometrics, 31(3), 307–327. https://doi.org/10.1016/0304-4076(86)90063-1
• [2] Bezerra, P., & Albuquerque, P. (2017). Volatility forecasting via SVR–GARCH with mixture of Gaussian kernels. Computational Management Science, 14, 179–196. https://doi.org/10.1007/s10287-016-0267-0
• [3] Chen, S., Jeong, K., & Härdle, W. K. (2008). Support vector regression based GARCH model with application to forecasting volatility of financial returns. SFB 649 Discussion SFB 649 Discussion Paper 2008-014. https://dx.doi.org/10.2139/ssrn.2894286
• [4] Chhajer, P., Shah, M., & Kshirsagar, A. (2022). The applications of artificial neural networks, support vector machines, and long–short term memory for stock market prediction. Decision Analytics Journal, 2, 100015. https://doi.org/10.1016/j.dajour.2021.100015
• [5] Christensen, K., Siggaard, M., & Veliyev, B. (2022). A Machine learning approach to volatility forecasting. Journal of Financial Econometrics, nbac02. https://doi.org/10.1093/jjfinec/nbac020
• [6] Da Silva, I. N., Spatti, D. H., Flauzino, R. A., Liboni, L. H.,  Reis Alves, S. F. (2016). Artificial Neural Networks: A Practical Course (pp. 3-19). Springer. https://doi.org/10.1007/978-3-319-43162-8_1
• [7] D’Ecclesia, R. L., & Clementi, D. (2021). Volatility in the stock market: ANN versus parametric models. Annals of Operations Research, 299(1), 1101-1127. https://doi.org/10.1007/s10479-019-03374-0
• [8] Feng, H., Kong, F., & Xiao, Y. (2011). Vessel Traffic Flow Forecasting Model Study based on Support Vector Machine. In Shen, G., Huang, X. (Eds.), Advanced Research on Electronic Commerce, Web Application, and Communication. ECWAC 2011. Communications in Computer and Information Science, (vol. 143, pp. 446 – 451). Springer. https://doi.org/10.1007/978-3-642-20367-1_72
• [9] Filipovic, D., & Khalilzadeh, A. (2021). Machine Learning for Predicting Stock Return Volatility. Swiss Finance Institute Research Paper, 21-95. http://dx.doi.org/10.2139/ssrn.3995529
• [10] Fraz, T. R., Fatima, S., & Uddin, M. (2022). Modeling and Forecasting Stock Market Volatility of CPEC Founding Countries: Using Nonlinear Time Series and Machine Learning Models. JISR Management and Social Sciences & Economics, 20(1), 1–20. https://doi.org/10.31384/jisrmsse/2022.20.1.1
• [11] Gholami, R.,  Fakhari, N. (2017). Chapter 27 - Support Vector Machine: Principles, Parameters, and Applications. In Samui, P., Sekhar, S., and Balas, V. E., (Eds.), Handbook of Neural Computation, (vol. 2017, pp. 515-535). Academic Press. https://doi.org/10.1016/B978-0-12-811318-9.00027-2
• [12] Karasan, A., & Gaygısız, E. (2022). Volatility Prediction and Risk Management: An SVR-GARCH. SSRN. http://dx.doi.org/10.2139/ssrn.4285524
• [13] Kristjanpoller, W., Fadic, A., & Minutolo, M. C. (2014). Volatility forecast using hybrid neural network models. Expert Systems with Applications, 41(5), 2437-2442. https://doi.org/10.1016/j.eswa.2013.09.043
• [14] Markowitz, H. (1952). Portfolio selection. The Journal of Finance, 7(1), 77–91. https://doi.org/10.2307/2975974
• [15] Bildirici, M., & Ersin, Ö. (2014). Modeling Markov Switching ARMA-GARCH Neural Networks Models and an Application to Forecasting Stock Returns. The Scientific World Journal, 2014, 497941. https://doi.org/10.1155/2014/497941
• [16] Monfared, S. A., & Enke, D. (2014). Volatility Forecasting Using a Hybrid GJR-GARCH Neural Network Model. Procedia Computer Science, 36, 246-253. https://doi.org/10.1016/j.procs.2014.09.087
• [17] Rodríguez - Vargas, A. (2020). Forecasting Costa Rica inflation with machine learning methods. Latin American Journal of Central Banking, 1(1-4), 100012. https://doi.org/10.1016/j.latcb.2020.100012
• [18] Roghani, A. (2016). Artificial Neural Networks, Applications in Financial Forecasting. CreateSpace Independent Publishing Platform.
• [19] Satria, D. (2023). Predicting Banking Stock Prices Using RNN, LSTM, and GRU Approach. Applied Computer Science, 19(1), 82-84. https://doi.org/10.35784/acs-2023-06
• [20] Scholkopf, B.,  Smola, A. (2018). Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. Adaptive Computation and Machine Learning series. MIT Press.
• [21] Shen, Z., Wan, Q., & Leatham, D. J. (2021). Bitcoin Return Volatility Forecasting: A Comparative Study between GARCH and RNN. Risk and Financial Management, 14(7), 337. https://doi.org/10.3390/jrfm14070337
• [22] Sun, H., & Yu, B. (2020). Forecasting Financial Returns Volatility: A GARCH-SVR Model. Computational Economics, 55, 451–47. https://doi.org/10.1007/s10614-019-09896-w
• [23] Verma, S. (2021). Forecasting volatility of crude oil futures using a GARCH–RNN hybrid approach. Intelligent Systems in Accounting, Finance and Management, 28(2), 130–142. https://doi.org/10.1002/isaf.1489
• [24] Wang, L. (2005). Support Vector Machines: Theory and Applications. In Wang, L. (ed.), Studies in Fuzziness and Soft Computing ( vol. 177). Springer.
• [25] Y, X., Wen, X., & Y, X. (2023). Time series prediction and application based on multi-kernel support vector regression. Second International Symposium on Computer Applications and Information Systems, 12721. https://doi.org/10.1117/12.2683400
• [26] Yamaka, W., Srichaikul, W., & Maneejuk, P. (2021). Support Vector Machine-Based GARCH-type Models: Evidence from ASEAN-5 Stock Markets. In: Ngoc Thach, N., Kreinovich, V., Trung, N.D. (Eds.), Data Science for Financial Econometrics. Studies in Computational Intelligence (vol. 898, pp. 369-381). Springer, https://doi.org/10.1007/978-3-030-48853-6_26
• [27] Zahid, M., Iqbal, F., Koutmos, D. (2022). Forecasting Bitcoin Volatility Using Hybrid GARCH Models with Machine Learning. Risks, 10(12), 237. https://doi.org/10.3390/risks10120237
• [28] Zhang, C., Zhang, Y., Cucuringu, M., & Qian, Z. (2022). Volatility forecasting with machine learning and intraday commonality. arXiv. https://doi.org/10.48550/arXiv.2202.08962
• [29] Zhang, G. & Qian, G. (2021). Out-of-sample realized volatility forecasting: does the support vector regression compete combination methods. Applied Economics, 53(19), 2192-2205. https://doi.org/10.1080/00036846.2020.1856326