Consolidation of Time Series Models for the Prediction of XUTEK Index and Technology Stocks in Istanbul Stock Exchange during Pandemic Period

Abstract

Due to the closure experienced during the pandemic, many investors divert their investments to different exchanges. In this sense, it has been observed that while sectors such as transportation, banking, and services have seriously lost value, especially the technology sector has come forward and gained value. In this research, we move the study one step forward by proposing a consolidated forecast system instead of employing a model to estimate the price of the Istanbul Stock Exchange Technology Index (XUTEK) which consists of 19 technology companies traded in BIST, and technology stocks. Stock movements during the pandemic period between 01.01.2020 and 01.09.2020, when technology stocks gained considerable value, are investigated to estimate the price of XUTEK. For each technology stock and XUTEK index, five different time series models are modeled namely, Holt’s linear trend, simple exponential smoothing, Holt–Winter’s additive, Holt–Winter’s multiplicative, and ARIMA. After that, five different time series models are consolidated with six diverse consolidation methods, namely, SA, SATA, MB, VB, VBP2 and VBP3 in order to get a more robust stock price prediction model. Experiment results demonstrate that the utilization of the VBP2 consolidation technique presents remarkable results with 2.6903 of MAPE for estimating the price of the XUTEK index and 19 technology stocks.

Keywords

• Decision Consolidation
• Istanbul Stock Exchange
• Stock Prediction
• Time Series Analysis
• XUTEK Index Forecast

References

1. [1] Li F., Zhong J., He F., Wang H., Lin J., Yu M., 2022. Stock market fluctuation and stroke incidence: A time series study in Eastern China. Social Science and Medicine, 296, pp. 1-6.
2. [2] Takyi P.O., Bentum-Ennin I., 2021. The impact of COVID-19 on stock market performance in Africa: A Bayesian structural time series approach. Journal of Economics and Business, 115, pp. 1-10.
3. [3] Satrio C.B.A., Darmawan W., Nadia B.U., Hanafiah N., 2021. Time series analysis and forecasting of coronavirus disease in Indonesia using ARIMA model and PROPHET. Procedia Computer Science, 179, pp. 524-532.
4. [4] Adebayo T.S., Akinsola G.D., Kirikkaleli D., Bekun F.V., Umarbeyli S., Osemeahon O.S., 2021. Economic performance of Indonesia amidst CO2 emissions and agriculture: a time series analysis. Environmental Science and Pollution Research, 28(35), pp. 47942-47956.
5. [5] Reinosch, E., Gerke, M., Riedel, B., Schwalb, A., Ye, Q., & Buckel, J., 2021. Rock glacier inventory of the western Nyainqêntanglha Range, Tibetan Plateau, supported by InSAR time series and automated classification. Permafrost and Periglacial Processes, 32(4), 657-672.
6. [6] Li, N., Arnold, D. M., Down, D. G., Barty, R., Blake, J., Chiang, F., ... & Heddle, N. M., 2022. From demand forecasting to inventory ordering decisions for red blood cells through integrating machine learning, statistical modeling, and inventory optimization. Transfusion, 62(1), 87-99.
7. [7] Chen, T., Song, C., Ke, L., Wang, J., Liu, K., & Wu, Q., 2021. Estimating seasonal water budgets in global lakes by using multi-source remote sensing measurements. Journal of Hydrology, 593, 125781.
8. [8] ElBerry N.A., Goeminne S., 2021. Fiscal transparency, fiscal forecasting and budget credibility in developing countries. Journal of Forecasting, 40(1), pp. 144-161.

9. [9] Nguyen H.M., Turk P.J., McWilliams A.D., 2021. Forecasting covid-19 hospital census: A multivariate time-series model based on local infection incidence. JMIR Public Health and Surveillance, 7(8), pp. 1-13.
10. [10] Fuladlu K., Riza M., Ilkan M., 2021. Monitoring urban Sprawl using time-series data: Famagusta region of Northern Cyprus. SAGE Open, 11(2), pp. 1-13.
11. [11] Varela S., Pederson T., Bernacchi C.J., Leakey A.D., 2021. Understanding growth dynamics and yield prediction of sorghum using high temporal resolution Uav imagery time series and machine learning. Remote Sensing, 13(9), pp. 1-17.
12. [12] Sun Z., Li Q., Jin S., Song Y., Xu S., Wang X., Jiang, D., 2022. Simultaneous Prediction of Wheat Yield and Grain Protein Content Using Multitask Deep Learning from Time-Series Proximal Sensing. Plant Phenomics, 2022, pp. 1-13.
13. [13] Jha B.K., Pande S., 2021. Time series forecasting model for supermarket sales using FB-prophet. Paper presented at 5th International Conference on Computing Methodologies and Communication, Erode, India, 8-10 April.
14. [14] Özeroğlu A.İ., 2021. Personal loan sales forecasting through time series analysis. Prizren Social Science Journal, 5(1), pp. 44-51.
15. [15] Heaton C., Ponomareva N., Zhang Q., 2020. Forecasting models for the Chinese macroeconomy: The simpler the better? Empirical Economics, 58(1), pp. 139-167.
16. [16] Elsayed A.M.M., 2021. Forecasting EGX30 index time series using vector autoregressive models VARS. International Journal of Statistics and Applied Mathematics, 6(2), pp. 6-20.
17. [17] Yasar H., Kilimci Z.H., 2020. US Dollar/Turkish Lira exchange rate forecasting model based on deep learning methodologies and time series analysis. Symmetry, 12(9), pp. 1553-1571.
18. [18] Wang Y., Guo Y., 2020. Forecasting method of stock market volatility in time series data based on mixed model of ARIMA and XGBoost. Chin Commun, 17(3), pp. 205-221.
19. [19] Pandey V.S., Bajpai A., 2019. Predictive efficiency of ARIMA and ANN models: A case analysis of nifty fifty in Indian stock market. Int J Appl Eng Res, 14(2), pp. 232-244.
20. [20] Yakut E., Elmas B., Yavuz S., 2014. Yapay sinir ağları ve destek vektör makineleri yöntemleriyle borsa endeksi tahmini. Süleyman Demirel Üniversitesi İktisadi İdari Bilimler Fakültesi Dergisi, 19(1), pp. 139-157.
21. [21] Kutlu B., Badur B., 2009. Yapay sinir ağları ile borsa endeksi tahmini. Yönetim Dergisi, 20(63), pp. 25-40.
22. [22] Wang J., Sun T., Liu B., Cao Y., Wang D., 2018. Financial markets prediction with deep learning. Paper presented at 17th IEEE International Conference on Machine Learning and Applications, Orlando, Florida, USA, 17-20 December.
23. [23] Shen S., Jiang H., Zhang T., 2012. Stock market forecasting using machine learning algorithms. MSc, Stanford University, Department of Electrical Engineering, Stanford, CA, USA.
24. [24] Livieris I.E., Pintelas E., Pintelas P.A., 2020. CNN–LSTM model for gold price time-series forecasting. Neural Comput Appl, 32(23), pp. 17351–17360.
25. [25] Keleş E., 2020. COVID-19 ve BİST-30 Endeksi Üzerine Kisa Dönemli Etkileri. Marmara Üniversitesi İktisadi ve İdari Bilimler Dergisi, 42(1), pp. 91-105.
26. [26] İlhan A., Akdeniz C., 2020. The impact of macroeconomic variables on the stock market in the time of Covid-19: The case of Turkey. Ekonomi Politika ve Finans Araştırmaları Dergisi, 5(3), pp. 893-912.
27. [27] Gülhan Ü., 2020. Covid-19 pandemisine BIST 100 reaksiyonu: Ekonometrik bir analiz. Electronic Turkish Studies, 15(4), pp. 497-509.
28. [28] Pakel C., Özen K., 2020. Daily volatility analysis of BIST 100 constituents between 2018-2020. Marmara Üniversitesi İktisadi ve İdari Bilimler Dergisi, 42(2), pp. 340-360.
29. [29] Teker S., Teker D., Demirel E., 2021. Market risk premiums in BIST 100 in the Covid era. Press Academia Procedia, 14(1), pp. 110-112.
30. [30] Hyndman R.J., Athanasopoulos G., 2018. Simple Exponential Smoothing, Forecasting: Principles and Practice, 2nd ed. Otexts, Melbourne, Australia.
31. [31] Holt C., 2004. Forecasting seasonals and trends by exponential weighted moving averages. Int J Forecast, 20, pp 5–10.
32. [32] Winters P.R., 1960. Forecasting sales by exponentially weighted moving averages. Manage Sci, 60(6), pp. 324–342.
33. [33] Box G. E., Jenkins G.M., Reinsel G.C., Ljung G.M., 2016. Time Series Analysis: Forecasting and Control. 2nd ed. Wiley, Hoboken, NJ, USA.
34. [34] Zhang G.P., 2003. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomp, 50, pp. 159-175.
35. [35] https://github.com/mrjbq7/ta-lib Accessed on January 2022.
36. [36] Richmond V., Jose R., Winkler R.L., 2008. Simple robust averages of forecasts: Some empirical results. Int J Forecast, 24, pp. 163–169.
37. [37] Lemke C., Gabrys B., 2010. Meta-learning for time series forecasting and forecast combination. Neurocomp, 73, pp. 2006–2016.
38. [38] Agnew C., 1985. Bayesian consensus forecasts of macroeconomic variables. J Forecast, 4, pp. 363–376.
39. [39] Stock J.H., Watson M.W., 1985. Combination forecasts of output growth in a seven-country data set. J Forecast, 23, pp. 405–430.
40. [40] Aksu C., Gunter S., 1992. An empirical analysis of the accuracy of SA, OLS, ERLS and NRLS combination forecasts. Int J Forecast, 8, pp. 27–43.
41. [41] Aiolfi M., Timmermann A., 2006. Persistence in forecasting performance and conditional combination strategies. J Econom, 127(1–2), pp. 31–53.