Forecasting realized volatility through ifnancial turbulence and neural networks

• Authors: Hugo Gobato Souto , Amir Moradi

Abstracts

EN

This paper introduces and examines a novel realized volaitlity forecasting model that makes use of Long Short-Term Memory (LSTM) neural networks and the risk metric finan cial turbulence (FT). The proposed model is compared to vife alternavtie models, of which two incorporate LSTM neu ral networks and the remaining three include GARCH(1,1), EGARCH(1,1), and HAR models. The results of this paper demonstrate that the proposed model yields statistically significantly more accurate and robust forecasts than all other studied models when applied to stocks with middleto-high volatility. Yet, considering low-volatility stocks, it can only be confidently afirmed that the proposed model yields statistically significantly more robust forecasts rela itve to all other models considered.

• Publisher: Uniwersytet Ekonomiczny w Poznaniu
• Journal: Economics and Business Review
• Year: 2023
• Volume: 9
• Issue: 2
• Pages: 133-159

Dates

published

2023

Contributors

author

Hugo Gobato Souto

author

Amir Moradi

References

• Aaltio, J. (2022). Volatility forecasting with artifcial neural networks [unpublished PHD dissertaotin]. Hanken School of Economics. hpts://helda.helsinki./fidhanken/ bitstream/handle/10227/509483/Aaltio_Juho.pdf?sequence=1
• Andersen, T. M., & Bollerslev, T. (1998). Answering the skeptics: Yes, standard volati - lity models do provide accurate forecasts. International Economic Review , 39(4), 885. htps://doi.org/10.2307/2527343
• Awais, M., Raza, M., Singh, Y., Bashir, K., Manzoor, U., Islam, S., & Rodrigues, J. J. P. C. (2021). LSTM-based emootin detecotin using physiological signals: IoT framework for healthcare and distance learning in COVID-19. IEEE Internet of Things Journal, 8(23), 16863-16871. htps://doi.org/10.1109/jiot.2020.3044031
• Baofur, A. A., Feng, J., & Taylor, E. K. (2019). A hybrid arcftiial neural network-GJR mo - deling approach to forecasntig currency exchange rate volaltiity. Neurocompuntig , 365, 285-301. htps://doi.org/10.1016/j.neucom.2019.07.088
• Bauwens, L., Laurent, S., & Rombouts, J. V. (2006). Multivariate GARCH models: A su - rvey. Journal of Applied Econometrics, 21(1), 79-109. htps://doi.org/10.1002/ jae.842
• Black, F. (1986). Noise. Journal of Finance, 41, 529-543.
• Bollerslev, T. (1986). Generalized autoregressive condiotinal heteroskedasctiity. Journal of Econometrics, 31(3), 307-327. hpts://doi.org/10.1016/0304-4076(86)90063-1
• Borup, D., & Jakobsen, J. S. (2019). Capturing volatility persistence: A dynamically complete realized EGARCH-MIDAS model. Quantitative Finance , 19(11), 1839- 1855. htps://doi.org/10.1080/14697688.2019.1614653
• Brandt, M. W., & Jones, C. W. (2006). Volatility forecasting with range-based EGARCH models. Journal of Business & Economic Statistics , 24(4), 470-486. htps://doi. org/10.1198/073500106000000206
• Bucci, A. (2020). Realized volatility forecasting with neural networks. Journal of Financial Econometrics, 18(3), 502-531. hpts://doi.org/10.1093/jjnfiec/nbaa008
• Chen, Q., & Robert, C. (2022). Multivariate realized volatility forecasting with graph neural network. Proceedings of the Third ACM International Conference on AI in Finance. htps://doi.org/10.1145/3533271.3561663
• Chen, W., Yao, J., & Shao, Y. (2022). Volatility forecasting using deep neural network with mtie-series feature embedding. Ekonomska Istrazivanja-Economic Research, 1377-1401. htps://doi.org/10.1080/1331677x.2022.2089192
• D'Ecclesia, R. L., & Clementi, D. (2021). Volatility in the stock market: ANN versus pa - rametric models. Annals of Operations Research , 299(1-2), 1101-1127. htps:// doi.org/10.1007/s10479-019-03374-0
• Diebold, F. X., & Mariano, R. S. (1995). Comparing predictive accuracy. Journal of Business & Economic Stastictis , 13(3), 253-263. hpts://doi.org/10.2307/1392185
• Donaldson, R. G., & Kamstra, M. J. (1996a). Forecast combining with neural networks. Journal of Forecasting , 15(1), 49-61. htps://doi.org/10.1002/(SICI)1099- 131X(199601)15:1<49::AID-FOR604>3.0.CO;2-2
• Donaldson, R. G., & Kamstra, M. J. (1996b). A new dividend forecasntig procedure that rejects bubbles in asset prices: The case of 1929's stock crash. Review of Financial Studies, 9(2), 333-383. htps://doi.org/10.1093/rfs/9.2.333
• Donaldson, R. G., & Kamstra, M. J. (1997). An artifcial neural network-GARCH model for international stock return volatility. Journal of Empirical Finance, 4(1), 17-46. htps://doi.org/10.1016/s0927-5398(96)00011-4
• Engle, R. F. (1982). Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inaflotin. Econometrica, 50(4), 987-1007. hpts:// doi.org/10.2307/1912773
• Engle, R. F., Ghysels, E., & Sohn, B. (2013). Stock market volaltiity and macroeconomic fundamentals. The Review of Economics and Statistics , 95(3), 776-797. htps:// doi.org/10.1162/rest_a_00300
• Gajdka, J., & Pietraszewski, P. (2017). Stock price volatility and fundamental value: Evidence from Central and Eastern European countries. Economics and Business Review, 3(4), 28-46. htps://doi.org/10.18559/ebr.2017.4.2
• Garman, M. B., & Klass, M. J. (1980). On the estimation of security price volati - lities from historical data. The Journal of Business, 53(1), 67-68. htps://doi. org/10.1086/296072
• Graves, A., Liwicki, M., Fernández, S., Bertolami, R., Bunke, H., & Schmidhuber, J. (2009). A novel connectionist system for unconstrained handwriting recognition. IEEE Transactions on Paetrn Analysis and Machine Intelligence , 31(5), 855-868. htps://doi.org/10.1109/tpami.2008.137
• Hajizadeh, E., Seifi, A., Zarandi, M. H. F., & Turksen, I. (2012). A hybrid modeling ap - proach for forecasting the volatility of S&P 500 Index return. Expert Systems with Applications , 39(1), 431-436. htps://doi.org/10.1016/j.eswa.2011.07.033
• Hamid, A., & Iqbal, Z. (2004). Using neural networks for forecasting volatility of S&P 500 Index futures prices. Journal of Business Research, 57(10), 1116-1125. hpts:// doi.org/10.1016/s0148-2963(03)00043-2
• Harvey, D., Leybourne, S. J., & Newbold, P. (1997). Testing the equality of prediction mean squared errors. Internaotinal Journal of Forecasntig , 13(2), 281-291. hpts:// doi.org/10.1016/s0169-2070(96)00719-4
• Haugom, E., Westgaard, S., Solibakke, P. B., & Lien, G. (2010). Modelling day ahead Nord Pool forward price volatility: Realized volatility versus GARCH models . Internaotinal Conference on the European Energy Market. hpts://doi.org/10.1109/ eem.2010.5558687
• Hu, Y., Ni, J., & Wen, L. (2020). A hybrid deep learning approach by integrating LSTMANN networks with GARCH model for copper price volaltiity predicotin. Physica D: Nonlinear Phenomena, 557, 124907. hpts://doi.org/10.1016/j.physa.2020.124907
• Kambouroudis, D. S., McMillan, D. G., & Tsakou, K. (2016). Forecasting stock return volaltiity: A comparison of GARCH, implied volaltiity, and realized volaltiity models. Journal of Futures Markets, 36(12), 1127-1163. hpts://doi.org/10.1002/fut.21783
• Kamijo, K., & Tanigawa, T. (1990). Stock price paetrn recognition-a recurrent neural network approach. 1990 IJCNN Internaotinal Joint Conference on Neural Networks. htps://doi.org/10.1109/ijcnn.1990.137572
• Karsoliya, S., & Azad, M. (2012). Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture. International Journal of Engineering Trends and Technology, 3(6). hpt://www.ijejtournal.org/volume-3/issue-6/IJETTV3I6P206.pdf
• Khan, A. I. (2011). Financial Volatility forecasting by nonlinear support vector machi - ne heterogeneous autoregressive model: Evidence from Nikkei 225 Stock Index. International Journal of Economics and Finance . htps://doi.org/10.5539/ijef. v3n4p138
• Kritzman, M., & Li, Y. (2010). Skulls, financial turbulence, and risk management. Financial Analysts Journal, 66(5), 30-41. htps://doi.org/10.2469/faj.v66.n5.3
• Latoszek, M., & Ślepaczuk, R. (2020). Does the inclusion of exposure to volatility into diversified porotflio improve the investment results? Porotflio construction from the perspective of a Polish investor. Economics and Business Review, 6(1), 46-81. htps://doi.org/10.18559/ebr.2020.1.3
• Li, J. (2022). The comparison of LSTM, LGBM, and CNN in stock volatility pre - diction . Proceedings of the 2002 7th International Conference on Financial Innovation and Economic Development (ICFIED 2022). htps://doi.org/10.2991/ aebmr.k.220307.147
• Li, X., & Wu, X. (2015). Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recogniotin . Internaotinal Conference on Acoustics, Speech, and Signal Processing (ICASSP). htps://doi.org/10.1109/ icassp.2015.7178826
• Lin, Y., Lin, Z., Liao, Y., Li, Y., Xu, J., & Yan, Y. (2022). Forecasting the realized volatility of stock price index: A hybrid model integrantig CEEMDAN and LSTM. Expert Systems with Applications , 206, 117736. htps://doi.org/10.1016/j.eswa.2022.117736
• Liu, R., Demirer, R., Gupta, R., & Tiwari, A. K. (2020). Volatility forecasting with bi - variate multifractal models. Journal of Forecasting , 39(2), 155-167. htps://doi. org/10.1002/for.2619
• Liu, X., Yang, H., Gao, J., & Wang, C. (2021). FinRL: Deep reinforcement learning framework to automate trading in quantitative finance. Social Science Research Network. htps://doi.org/10.2139/ssrn.3955949
• Loang, O. K., & Ahmad, Z. (2021). Does volatility mediate the impact of analyst re - commendations on herding in Malaysian stock market? Economics and Business Review, 7(4), 54-71. htps://doi.org/10.18559/ebr.2021.4.4
• Maciel, L., Gomide, F., & Ballini, R. (2016). Evolving fuzzy-GARCH approach for finan - cial volaltiity modeling and forecasntig. Computaotinal Economics , 48(3), 379-398. htps://doi.org/10.1007/s10614-015-9535-2
• Mayer, H., Gomez, F., Wierstra, D., Nagy, I., Knoll, A., & Schmidhuber, J. (2006). A system for robotic heart surgery that learns to tie knots using Recurrent Neural Networks. Advanced Robotics , 22(13-14), 1521-1537. htps://doi.org/ 10.1163/156855308x360604
• Naidu, G. P., & Govinda, K. (2018). Bankruptcy predicotin using neural networks . 2018 2nd International Conference on Inventive Systems and Control (ICISC). htps:// doi.org/10.1109/icisc.2018.8399072
• Nystrup, P., Boyd, S., Lindström, E., & Madsen, H. (2019). Mul-tiperiod porotflio selec - iton with drawdown control. Annals of Operations Research , 282(1-2), 245-271. htps://doi.org/10.1007/s10479-018-2947-3
• Nystrup, P., Madsen, H., & Lindström, E. (2018). Dynamic porotflio opmtiizaotin across hidden market regimes. Quantitative Finance , 18(1), 83-95. htps://doi.org/10.1 080/14697688.2017.1342857
• Parkinson, M. H. (1980). The extreme value method for estimating the varian - ce of the rate of return. The Journal of Business, 53(1), 61-65. htps://doi. org/10.1086/296071
• Rodikov, G., & Antulov-Fantulin, N. (2022). Can LSTM outperform volatility-econome - tric models? ArXiv Preprint. htps://doi.org/10.48550/arXiv.2202.11581
• Rodriguez, J. (2018, July). The science behind OpenAI Five that just produced one of the greatest breakthrough in the history of AI. Towards Data Science. htps:// www.linkedin.com/pulse/science-behind-openai-vfie-just-produced-one-greatestjesus-rodriguez/
• Rogers, L. C. G., & Satchell, S. (1991). Estimating variance from high, low and closing prices. Annals of Applied Probability, 1 (4), 504-512. htps://doi.org/10.1214/ aoap/1177005835
• Rogers, L. C. G., Satchell, S., & Yoon, Y. (1994). Estimating the volatility of stock pri - ces: A comparison of methods that use high and low prices. Applied Financial Economics, 4(3), 241-247. htps://doi.org/10.1080/758526905
• Rossi, E., & De Magistris, P. S. (2014). Estimation of long memory in integrated va - riance. Econometric Reviews, 33(7), 785-814. htps://doi.org/10.1080/0747493 8.2013.806131
• Sahidullah, M., Patino, J., Cornell, S., Yin, R., Sivasankaran, S., Bredin, H., Korshunov, P., Bruti, A., Serizel, R., Vincent, E., Evans, N., Marcel, S., Squartini, S., & Barras, C. (2019). The speed submission to DIHARD II: Contributions & lessons learned . HAL (Le Centre Pour La Communication Scientifque Directe). htps://hal.inria.fr/ hal-02352840v2/file/Speed_DIHARDII_Manuscript.pdf
• Salisu, A. A., Demirer, R., & Gupta, R. (2022). Financial turbulence, systemic risk and the predictability of stock market volatility. Global Finance Journal, 52, 100699. htps://doi.org/10.1016/j.gfj.2022.100699
• Sheela, K. G., & Deepa, S. N. (2013). Review on methods to fix number of hidden neu - rons in neural networks. Mathematical Problems in Engineering , 425740. htps:// doi.org/10.1155/2013/425740
• Souto, H.G. (2023a) Distribution analysis of S&P 500 financial turbulence. Journal of Mathematical Finance , 13, 67-88. htps://doi.org/10.4236/jmf.2023.131005
• Souto, H.G. (2023b) Time series forecasting models for S&P 500 financial turbu - lence. Journal of Mathematical Finance , 13, 112-129. htps://doi.org/10.4236/ jmf.2023.131007
• Vidal, A., & Kristjanpoller, W. (2020). Gold volatility prediction using a CNN-LSTM ap - proach. Expert Systems with Applicaotins , 157, 113481. hpts://doi.org/10.1016/j. eswa.2020.113481
• Vujičić, T. M., Matijević, T., Ljucović, J., Balota, A., & Sevarac, Z. (2016). Comparative analysis of methods for determining number of hidden neurons in artifcial neural network. Central European Conference on Information and Intelligent Systems.
• White. (1988). Economic prediction using neural networks: The case of IBM daily stock returns. IEEE 1988 International Conference on Neural Networks. htps:// doi.org/10.1109/icnn.1988.23959
• Wilson, R. K., & Sharda, R. (1994). Bankruptcy prediction using neural networks. Decision Support Systems, 11(5), 545-557. https://doi.org/10.1016/0167- 9236(94)90024-8
• Wu, Y., Schuster, M., Chen, Z., Le, Q. V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., Klingner, J., Shah, A. S., Johnson, M., Liu, X., Kaiser, Ł., Gouws, S., Kato, Y., Kudo, T., Kazawa, H., ..., Dean, J. (2016). Google's neural machine translation system: Bridging the gap between human and machine transla - iton . ArXiv. htps://arxiv.org/pdf/1609.08144.pdf
• Yan, Y., & Yang, D. (2021). A stock trend forecast algorithm based on deep neural networks. Scientifc Programming , 1-7. htps://doi.org/10.1155/2021/7510641
• Yang, D., & Zhang, Q. (2000). Drift independent volatility estimation based on high, low, open, and close prices. The Journal of Business, 73(3), 477-492. htps://doi. org/10.1086/209650
• Zhu, X., Wang, H., Xu, L., & Li, H. (2008). Predicting stock index increments by neural networks: The role of trading volume under diefrent horizons. Expert Systems with Applicaotins , 34(4), 3043-3054. hpts://doi.org/10.1016/j.eswa.2007.06.023

Identifiers

DOI

10.18559/ebr.2023.2.737

Biblioteka Nauki

2231659