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 (BIST) 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 significant value, are analyzed in order to forecast the price of XUTEK. For each technology stock and XUTEK index, five different time series models are modeled namely, simple exponential smoothing, Holt’s linear trend, 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, VBP3 in order to get more robust stock price prediction model. Experiment results demonstrate that the usage of VBP2 consolidation model presents remarkable results with 2.6903 of MAPE for predicting the price of XUTEK index and 19 technology stocks.
Publisher
Kocaeli Journal of Science and Engineering
Subject
General Earth and Planetary Sciences,General Environmental Science
Reference21 articles.
1. Heaton, C., Ponomareva, N., Zhang, Q. (2020). Forecasting models for the Chinese macroeconomy: The simpler the better? Empir Econ 2020, 58(1), 139-167.
2. Elsayed, A. M. M. (2021). Forecasting EGX30 index time series using vector autoregressive models VARS. Int J Stat Appl Math, 6(2), 6-20.
3. 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), 1553-1571.
4. 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), 205-221.
5. 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), 232-244.