Simulation analysis of financial stock market based on machine learning and GARCH model

Issue title: Complex evolutionary artificial intelligence in cognitive digital twinning

Guest editors: Neal Wagner, Sundhararajan, Le Hoang Son and Meng Joo

Article type: Research Article

Authors: Tian, Jie^a | Wang, Yaoqiang^b | Cui, Wenjing^a | Zhao, Kun^{c; *}

Affiliations: [a] School of Economy and Trade, Hebei GEO University. Shijiazhuang, Hebei, China | [b] School of Economics and Management, Tsinghua University, Beijing, China | [c] Deloitte Touche Tohmatsu Limited, Beijing, China

Correspondence: [*] Corresponding author. Kun Zhao, Deloitte Touche Tohmatsu Limited, Beijing, China. E-mail: [email protected].

Abstract: With the rapid development of the world’s financial industry, the complexity and relevance of risks are gradually increasing. At present, there are still some deficiencies in the model for measuring financial risk. In view of this, this study analyzes the financial stock market and combines VAR model and GARCH model to conduct financial analysis. Moreover, this study uses the standard deviation in the statistical characteristics of the data to characterize the fluctuation of futures, and then uses the univariate GARCH model to measure the fluctuation. In addition, this study combines the examples to analyze the effectiveness of the model, and compares the predicted data with the actual data to verify the model performance. The results show that the algorithm proposed in this paper has certain effectiveness, and through this research algorithm, investors, speculators or macro decision makers in the futures market can obtain some inspiration.

Keywords: VAR model, GARCH model, financial stocks, market, simulation analysis

DOI: 10.3233/JIFS-189225

Journal: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 2, pp. 2277-2287, 2021