Can we forecast stock movements during uncertain times? An application of Markov Chain Method on Turkish Energy Sector

Öz

Stock market forecasting has always been difficult for investors, academics, and businesses. The uncertainty created by the COVID-19 epidemic has further added to the difficulty. The goal of this study is to see if using the transition matrix in the Markov chain, the stock return percentages of the energy sectors, which are becoming increasingly important in all aspects of our lives, can be used to estimate the risky situation on the stock markets in the COVID-19 period compared to the previous day. The daily stock movement fluctuations of 18 Turkish energy businesses trading in the BIST100 index over one year (2020/04-2021/04) are examined in this study. The transitions between the states, as well as their numbers, were determined in the study, and then the transition probability matrix was produced. Finally, based on previous data, the price movement for the following day was forecasted with a high degree of certainty. By comparing real and synthetic data, the accuracy of Markov chain predictions can be proved. The results demonstrate that utilizing Markov chains to anticipate stock market movements has a 77.77 percent success rate in the COVID-19 timeframe. The study's findings are intended to be beneficial to businesses and investors.

Anahtar Kelimeler

• Energy Sector
• Markov Chain
• Stock
• Transition Probability Matrix
• Covid-19

Kaynakça

1. Affonso, F., Dias, T. M. R., & Pinto, A. L. (2021). Financial Times Series Forecasting of Clustered Stocks. Mobile Networks and Applications, 26(1), 256–265. https://doi.org/10.1007/s11036-020-01647-8
2. Alp, S., & Öz, E. (2009). Markov Zinciri Yöntemi İle Taşınabilir Bilgisayar Tercihlerinin Analizi. Akademik İncelemeler Dergisi, 4(2), 37–55. http://dergipark.ulakbim.gov.tr/akademikincelemeler/article/view/5000063793
3. Ashraf, B. N. (2020). Stock markets’ reaction to COVID-19: Cases or fatalities? Research in International Business and Finance, 54(May), 101249. https://doi.org/10.1016/j.ribaf.2020.101249
4. Attigeri, G. V., Manohara Pai, M. M., Pai, R. M., & Nayak, A. (2016). Stock market prediction: A big data approach. IEEE Region 10 Annual International Conference, Proceedings/TENCON, 2016-Janua. https://doi.org/10.1109/TENCON.2015.7373006
5. Bebarta, D. K., Leflann, L. A. N. N., Functional, C., & Ann, L. (2012). Different Polynomial Functional Link Artificial Neural Networks. 178–182.
6. Budiharto, W. (2021). Data science approach to stock prices forecasting in Indonesia during Covid-19 using Long Short-Term Memory (LSTM). Journal of Big Data, 8(1), 47. https://doi.org/10.1186/s40537-021-00430-0
7. Chandra, R., & He, Y. (2021). Bayesian neural networks for stock price forecasting before and during COVID-19 pandemic. PLOS ONE, 16(7), e0253217. https://doi.org/10.1371/journal.pone.0253217
8. Chen, D., & Yuan, X. (2004). A Markov model for seasonal forecast of Antarctic sea ice. Journal of Climate, 17(16), 3156–3168. https://doi.org/10.1175/1520-0442(2004)017<3156:AMMFSF>2.0.CO;2

9. Coyne, S., Madiraju, P., & Coelho, J. (2018). Forecasting stock prices using social media analysis. Proceedings - 2017 IEEE 15th International Conference on Dependable, Autonomic and Secure Computing, 2017 IEEE 15th International Conference on Pervasive Intelligence and Computing, 2017 IEEE 3rd International Conference on Big Data Intelligence and Compu, 2018-Janua, 1031–1038. https://doi.org/10.1109/DASC-PICom-DataCom-CyberSciTec.2017.169
10. Erfani, A., & Samimi, A. J. (2009). Long memory forecasting of stock price index using a fractionally differenced arma model. Journal of Applied Sciences Research, 5(10), 1721–1731.
11. Gurav, U. P., & Kotrappa, S. (2020). Impact of COVID 19 on Stock Market performance using Efficient and Predictive LBL-LSTM based Mathematical Model. International Journal on Emerging Technologies, 11(4), 108–115.
12. GÜNDÜZ, S., & KIRAL, S. G. (2020). Markov Zincirleri Kullanılarak Seçmen Tercihlerinin Tahmin Edilmesi. Çukurova Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 29(1), 270–281. https://doi.org/10.35379/cusosbil.671862
13. Hamadu, D., & Ibiwoye, A. (2010). Modelling and Forecasting the Volatility of the Daily Returns of Nigerian Insurance Stocks. International Business Research, 3(2), 106–116. https://doi.org/10.5539/ibr.v3n2p106
14. He, W., Guo, L., Shen, J., & Akula, V. (2016). Social media-based forecasting: A case study of tweets and stock prices in the financial services industry. Journal of Organizational and End User Computing, 28(2), 74–91. https://doi.org/10.4018/JOEUC.2016040105
15. Honeycutt, A. A., Boyle, J. P., Broglio, K. R., Thompson, T. J., Hoerger, T. J., Geiss, L. S., & Narayan, K. M. V. (2003). A dynamic Markov model for forecasting diabetes prevalence in the United States through 2050. Health Care Management Science, 6(3), 155–164. https://doi.org/10.1023/A:1024467522972
16. Ildırar, M., & Kıral, E. (2018). Otomotiv Sektörü Piyasa Yapısı Markov Analizi Uygulaması. Karahan Kitabevi.
17. İskenderoğlu, Ö., Karadeniz, E., & Ayyildiz, N. (2015). Enerji Sektörünün Finansal Analizi: Türkiye Ve Avrupa Enerji Sektörü Karşılaştırması. İşletme Ve İktisat Çalışmaları Dergisi, 3(3), 86-97.
18. Kaiser, T. (2005). One-Factor-GARCH Models for German Stocks - Estimation and Forecasting. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.1063
19. Karatepe, S. (2011). Yenilenebilir Enerji Kaynaklarından Rüzgâr İle Üretilen Enerjinin Ekonomik Değerinin Markov Zinciri İle Modellenmesi Ve Yalova İlinde Bir Uygulama (Master's Thesis, Uludağ Üniversitesi).
20. Kostadinova, V., Georgiev, I., Mihova, V., & Pavlov, V. (2021). An application of Markov chains in stock price prediction and risk portfolio optimization. AIP Conference Proceedings, 2321(February), 030018. https://doi.org/10.1063/5.0041119
21. Lee, M. C., Liao, J. S., Yeh, S. C., & Chang, J. W. (2020). Forecasting the Short-term Price Trend of Taiwan Stocks with Deep Neural Network. ACM International Conference Proceeding Series, 296–299. https://doi.org/10.1145/3377571.3377608
22. Makridakis, S., Hogarth, R. M., & Gaba, A. (2009). Forecasting and uncertainty in the economic and business world. International Journal of Forecasting, 25(4), 794–812. https://doi.org/10.1016/j.ijforecast.2009.05.012
23. Mondal, P., Shit, L., & Goswami, S. (2014). Study of Effectiveness of Time Series Modeling (Arima) in Forecasting Stock Prices. International Journal of Computer Science, Engineering and Applications, 4(2), 13–29. https://doi.org/10.5121/ijcsea.2014.4202
24. Onwukwe, C. E., Samson, T. K., & Lipcsey, Z. (2014). Modelling and Forecasting Daily Returns Volatility of Nigerian Banks. 10(15), 449–467.
25. Öztürk, A., (2004). Yöneylem Araştırması, Genişletilmiş 9. Baskı, Bursa: Ekin Kitabevi Yayınları, 2004.
26. Rounaghi, M. M., & Nassir Zadeh, F. (2016). Investigation of market efficiency and Financial Stability between S&P 500 and London Stock Exchange: Monthly and yearly Forecasting of Time Series Stock Returns using ARMA model. Physica A: Statistical Mechanics and Its Applications, 456, 10–21. https://doi.org/10.1016/j.physa.2016.03.006
27. Sharma, G. D., Erkut, B., Jain, M., Kaya, T., Mahendru, M., Srivastava, M., Uppal, R. S., & Singh, S. (2020). Sailing through the COVID-19 Crisis by Using AI for Financial Market Predictions. Mathematical Problems in Engineering, 2020, 1–18. https://doi.org/10.1155/2020/1479507
28. Skehin, T., Crane, M., & Bezbradica, M. (2018). Day ahead forecasting of FAANG stocks using ARIMA, LSTM networks and wavelets. CEUR Workshop Proceedings, 2259, 186–197.
29. Štrumbelj, E., & Vračar, P. (2012). Simulating a basketball match with a homogeneous Markov model and forecasting the outcome. International Journal of Forecasting, 28(2), 532–542. https://doi.org/10.1016/j.ijforecast.2011.01.004
30. Tjung, L., Kwon, O., & Tseng, K. (2012). Comparison study on neural network and ordinary least squares model to stocks ’. Academy of Information and Management Sciences Journal, 15(1), 1–36.
31. Yang, L., He, M., Zhang, J., & Vittal, V. (2015). Support-vector-machine-enhanced markov model for short-term wind power forecast. IEEE Transactions on Sustainable Energy, 6(3), 791–799. https://doi.org/10.1109/TSTE.2015.2406814
32. Zhang, D., Hu, M., & Ji, Q. (2020). Financial markets under the global pandemic of COVID-19. Finance Research Letters, 36(March), 101528. https://doi.org/10.1016/j.frl.2020.101528
33. Zhou, F., Zhou, H. min, Yang, Z., & Yang, L. (2019). EMD2FNN: A strategy combining empirical mode decomposition and factorization machine based neural network for stock market trend prediction. Expert Systems with Applications, 115, 136–151. https://doi.org/10.1016/j.eswa.2018.07.065
34. Zhou, H. R., & Wei, Y. H. (2010). Stocks market modeling and forecasting based on HGA and wavelet neural networks. Proceedings - 2010 6th International Conference on Natural Computation, ICNC 2010, 2(Icnc), 620–625. https://doi.org/10.1109/ICNC.2010.5583136