Abstract
In the current context of the Russian-Ukrainian conflict, the world economic situation is in constant turmoil. The aim of this study is to find the best model with the lowest error rate and strongest predictive power by using a daily closing price series to forecast the natural gas index SPGSNG, which is most affected by the current situation. This study has two main research components. Firstly, we check whether the index movements can be predicted with some degree of accuracy before and during the Russian-Ukrainian conflict (ARIMA + GARCH). Secondly, we examined the performance of a machine learning model (Random Forest) for predicting market indices. Based on actual and predicted stock index prices, we found that the Random Forest model was more accurate in its predictions. Applying a more accurate forecasting model to the market allows investors to effectively hedge against market risks associated with high price volatility.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Mandelbrot, B.B.: How long is the cost of Britain? Statistical self-similarity and fractional dimension (1976)
Engle, R.E.: Autoregressive conditional heteroskedasticity with estimates of the variance of united kingdom inflation. Econometrica 50(50) (1982)
Mark, M., Carhart, F.: On persistence in mutual fund performance. J. Finan. 52(1), 57–82 (1997)
Zhou Liang, F., Jiang Lian, S.: Research on factor allocation of major assets driven by machine learning. J. Finan. Develop. Res. 08, 55–63 (2022)
Yu Chuangmin, F., Gong Yutian, S., Wang Feng, T.: Predicting stock prices with text and price combined model. Data Anal. Knowl. Discov. 2(12), 33–42 (2018)
Harvey, C.R., Liu, Y., Zhu, H.: … and the cross-section of expected returns. Rev. Finan. Stud. 29(1) (2016)
Hou, K.F., Xue, C.S., Zhang, L.T.: Replicating anomalies. Rev. Finan. Stud. 33(5) 2019–2133 (2020)
Fuster, A., Goldsmith-Pinkham, P., Ramadorai, T., Walther, A.: Predictably unequal? the effects of machine learning on credit markets. J. Financ. 77, 5–47 (2022)
Zhou Liang, F., Li Ning, S.: Research on the factor allocation of major assets based on post-LASSO method. J. Finan. Develop. Res. 11, 39–47 (2021)
Lin, N.F., Qin, J.S.: Forecast of a-share stock change based on random forest. J. Univ. Shanghai Sci. Technol. 40(03), 267–273 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, J., Yan, R., Zhang, Y. (2023). Stock Market Forecasting Using the ARIMA, GARCH and Random Forest Model During The Russia–Ukraine War. In: Dang, C.T., Cifuentes-Faura, J., Li, X. (eds) Proceedings of the 2nd International Conference on Business and Policy Studies. CONF-BPS 2023. Applied Economics and Policy Studies. Springer, Singapore. https://doi.org/10.1007/978-981-99-6441-3_89
Download citation
DOI: https://doi.org/10.1007/978-981-99-6441-3_89
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-6440-6
Online ISBN: 978-981-99-6441-3
eBook Packages: Political Science and International StudiesPolitical Science and International Studies (R0)