(Equipe AMIPS, Ecole Mohammadia d’Ingénieurs, Mohammed V University in Rabat, Morocco)(2) Abdelaziz Berrado
(Equipe AMIPS, Ecole Mohammadia d’Ingénieurs, Mohammed V University in Rabat, Morocco)(3) Loubna Benabbou
(Université du Québec à Rimouski (UQAR), Campus de Lévis, Canada)*corresponding author
AbstractAccurately predicting extreme stock market fluctuations at the right time will allow traders and investors to make better-informed investment decisions and practice more efficient financial risk management. However, extreme stock market events are particularly hard to model because of their scarce and erratic nature. Moreover, strong trading strategies, market stress tests, and portfolio optimization largely rely on sound data. While the application of generative adversarial networks (GANs) for stock forecasting has been an active area of research, there is still a gap in the literature on using GANs for extreme market movement prediction and simulation. In this study, we proposed a framework based on GANs to efficiently model stock prices’ extreme movements. By creating synthetic real-looking data, the framework simulated multiple possible market-evolution scenarios, which can be used to improve the forecasting quality of future market variations. The fidelity and predictive power of the generated data were tested by quantitative and qualitative metrics. Our experimental results on S&P 500 and five emerging market stock data show that the proposed framework is capable of producing a realistic time series by recovering important properties from real data. The results presented in this work suggest that the underlying dynamics of extreme stock market variations can be captured efficiently by some state-of-the-art GAN architectures. This conclusion has great practical implications for investors, traders, and corporations willing to anticipate the future trends of their financial assets. The proposed framework can be used as a simulation tool to mimic stock market behaviors.
KeywordsExtreme events prediction; Time series generation; Stock markets simulation; Generative adversarial networks; Long short-term memory
|
DOIhttps://doi.org/10.26555/ijain.v9i2.898 |
Article metricsAbstract views : 694 | PDF views : 230 |
Cite |
Full Text Download
|
References
[1] S. Ghosh, “COVID-19, stock market, exchange rate, oil prices, unemployment, inflation, geopolitical risk nexus, the case of the BRICS nations: Evidence quantile regression,” Impact Glob. Issues Int. Trade, pp. 86–105, Jun. 2021, doi: 10.4018/978-1-7998-8314-2.CH005.
[2] P. F. Dai, X. Xiong, Z. Liu, T. L. D. Huynh, and J. Sun, “Preventing crash in stock market: The role of economic policy uncertainty during COVID-19,” Financ. Innov., vol. 7, no. 1, pp. 1–15, Dec. 2021, doi: 10.1186/S40854-021-00248-Y.
[3] H. Liu, A. Manzoor, C. Wang, L. Zhang, and Z. Manzoor, “The COVID-19 Outbreak and Affected Countries Stock Markets Response,” Int. J. Environ. Res. Public Heal. 2020, vol. 17, no. 8, p. 2800, Apr. 2020, doi: 10.3390/IJERPH17082800.
[4] M. Mazur, M. Dang, and M. Vega, “COVID-19 and the march 2020 stock market crash. Evidence from S&P1500,” Financ. Res. Lett., vol. 38, p. 101690, Jan. 2021, doi: 10.1016/J.FRL.2020.101690.
[5] M. Uddin, A. Chowdhury, K. Anderson, and K. Chaudhuri, “The effect of COVID – 19 pandemic on global stock market volatility: Can economic strength help to manage the uncertainty?,” J. Bus. Res., vol. 128, pp. 31–44, May 2021, doi: 10.1016/J.JBUSRES.2021.01.061.
[6] I. Shaikh, “Impact of COVID-19 pandemic disease outbreak on the global equity markets,” Econ. Res. Istraživanja, vol. 34, no. 1, pp. 2317–2336, 2021, doi: 10.1080/1331677X.2020.1863245.
[7] A. Coletta et al., “Towards Realistic Market Simulations: A Generative Adversarial Networks Approach,” ICAIF 2021 - 2nd ACM Int. Conf. AI Financ., pp. 1-9, Nov. 2021, doi: 10.1145/3490354.3494411.
[8] G. S. Atsalakis and K. P. Valavanis, “Surveying stock market forecasting techniques – Part II: Soft computing methods,” Expert Syst. Appl., vol. 36, no. 3, pp. 5932–5941, Apr. 2009, doi: 10.1016/J.ESWA.2008.07.006.
[9] C. L. Chang, M. McAleer, and Y. A. Wang, “Herding behaviour in energy stock markets during the Global Financial Crisis, SARS, and ongoing COVID-19*,” Renew. Sustain. Energy Rev., vol. 134, p. 110349, Dec. 2020, doi: 10.1016/J.RSER.2020.110349.
[10] N. Engelhardt, M. Krause, D. Neukirchen, and P. N. Posch, “Trust and stock market volatility during the COVID-19 crisis,” Financ. Res. Lett., vol. 38, p. 101873, Jan. 2021, doi: 10.1016/J.FRL.2020.101873.
[11] M. Ambros, M. Frenkel, T. L. D. Huynh, and M. Kilinc, “COVID-19 pandemic news and stock market reaction during the onset of the crisis: evidence from high-frequency data,”, vol. 28, no. 19, pp. 1686–1689, 2020, doi: 10.1080/13504851.2020.1851643.
[12] W. Jiang, “Applications of deep learning in stock market prediction: Recent progress,” Expert Syst. Appl., vol. 184, p. 1-97, Dec. 2021, doi: 10.1016/J.ESWA.2021.115537.
[13] Y. Lecun, Y. Bengio, and G. Hinton, “Deep learning,” Nat. 2015 5217553, vol. 521, no. 7553, pp. 436–444, May 2015, doi: 10.1038/nature14539.
[14] S. C. Huang, C. F. Wu, C. C. Chiou, and M. C. Lin, “Intelligent FinTech Data Mining by Advanced Deep Learning Approaches,” Comput. Econ., vol. 59, no. 4, pp. 1407–1422, Apr. 2022, doi: 10.1007/S10614-021-10118-5.
[15] 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, Oct. 2018, doi: 10.1016/J.EJOR.2017.11.054.
[16] D. Murekachiro, T. Mokoteli, and H. Vadapalli, “Predicting emerging and frontier stock markets using deep neural networks,” Adv. Intell. Syst. Comput., vol. 1037, pp. 899–918, 2020, doi: 10.1007/978-3-030-29516-5_68.
[17] A. E. de Oliveira Carosia, G. P. Coelho, and A. E. A. da Silva, “Investment strategies applied to the Brazilian stock market: A methodology based on Sentiment Analysis with deep learning,” Expert Syst. Appl., vol. 184, pp. 1-12, Dec. 2021, doi: 10.1016/J.ESWA.2021.115470.
[18] W. Lu, J. Li, J. Wang, and L. Qin, “A CNN-BiLSTM-AM method for stock price prediction,” Neural Comput. Appl., vol. 33, no. 10, pp. 4741–4753, May 2021, doi: 10.1007/S00521-020-05532-Z.
[19] J. Engelmann and S. Lessmann, “Conditional Wasserstein GAN-based oversampling of tabular data for imbalanced learning,” Expert Syst. Appl., vol. 174, p. 114582, Jul. 2021, doi: 10.1016/J.ESWA.2021.114582.
[20] K. Armanious et al., “MedGAN: Medical image translation using GANs,” Comput. Med. Imaging Graph., vol. 79, p. 101684, Jan. 2020, doi: 10.1016/J.COMPMEDIMAG.2019.101684.
[21] M. K. Baowaly, C. C. Lin, C. L. Liu, and K. T. Chen, “Synthesizing electronic health records using improved generative adversarial networks,” J. Am. Med. Informatics Assoc., vol. 26, no. 3, pp. 228–241, Mar. 2019, doi: 10.1093/JAMIA/OCY142.
[22] G. Ramponi, P. Protopapas, M. Brambilla, and R. Janssen, “T-CGAN: Conditional Generative Adversarial Network for Data Augmentation in Noisy Time Series with Irregular Sampling,” pp.1-12 Nov. 2018,. doi: 10.48550/arXiv.1811.08295.
[23] S. Takahashi, Y. Chen, and K. Tanaka-Ishii, “Modeling financial time-series with generative adversarial networks,” Phys. A Stat. Mech. its Appl., vol. 527, pp. 1-12, Aug. 2019, doi: 10.1016/J.PHYSA.2019.121261.
[24] W. Tovar, “Deep Learning Based on Generative Adversarial and Convolutional Neural Networks for Financial Time Series Predictions,” Aug. 2020, Accessed: May 02, 2023. doi: 10.48550/arXiv.2008.08041.
[25] K. Zhang, G. Zhong, J. Dong, S. Wang, and Y. Wang, “Stock Market Prediction Based on Generative Adversarial Network,” Procedia Comput. Sci., vol. 147, pp. 400–406, Jan. 2019, doi: 10.1016/J.PROCS.2019.01.256.
[26] I. Goodfellow et al., “Generative Adversarial Networks,” Commun. ACM, vol. 63, no. 11, pp. 139–144, Jun. 2014, doi: 10.1145/3422622.
[27] I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. Courville, “Improved Training of Wasserstein GANs,” Adv. Neural Inf. Process. Syst., vol. 2017-December, pp. 5768–5778, Mar. 2017, Accessed: May 02, 2023. doi: 10.48550/arXiv.1704.00028.
[28] C. Esteban, S. L. Hyland, and G. Rätsch, “Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs,” pp. 1-13, Jun. 2017, Accessed: May 02, 2023. doi: 10.48550/arXiv.1706.02633.
[29] J. Yoon, D. Jarrett, and M. van der Schaar, “Time-series Generative Adversarial Networks,” Adv. Neural Inf. Process. Syst., vol. 32, pp. 1-11, 2019. Available at: https://papers.nips.cc/paper/8789-time-series-generative-adversarial-networks.
[30] Z. Lin, A. Jain, C. Wang, G. Fanti, and V. Sekar, “Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions,” Proc. ACM SIGCOMM Internet Meas. Conf. IMC, vol. 2020-Oct, pp. 464–483, doi: 10.1145/3419394.3423643.
[31] M. Wiese, L. Bai, B. Wood, and H. Buehler, “Deep Hedging: Learning to Simulate Equity Option Markets,” SSRN Electron. J., Oct. 2019, pp.1-13, doi: 10.2139/SSRN.3470756.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
___________________________________________________________
International Journal of Advances in Intelligent Informatics
ISSN 2442-6571 (print) | 2548-3161 (online)
Organized by UAD and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
W: http://ijain.org
E: info@ijain.org (paper handling issues)
andri.pranolo.id@ieee.org (publication issues)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0