Academic Journal of Business & Management, 2021, 3(10); doi: 10.25236/AJBM.2021.031020.
Ming Li1, Hefei Wang2, Hua Fang3
1&3Business School, University of Shanghai For Science and Technology, Shanghai, 200093, China
2School of Public Management, Inner Mongolia University, Hohhot, Inner Mongolia, 010021, China
In recent years, the development of FinTech has moved from behind the scenes to the front, greatly promoting the development of innovation and high-quality supply in the financial sector. The development level of China's FinTech is generally leading in the world, and many listed FinTech companies have brought vitality to the financial market. But on the other hand, fintech also contributes to market volatility. Reasonable prediction of its trend and prevention of investment risks are still important issues. In this paper, CNI Xiangmi Lake FinTech Index, which can measure the overall performance of China's FinTech listed companies, is selected as the research object, and GARCH model and BP neural network model are used to conduct empirical analysis and forecast research on the index. The results show that the two time series models can fit the curve and the actual trend well. Compared with the prediction accuracy, the prediction effect of GARCH model is better than BP neural network model.
FinTech; GARCH model; BP neural network model.; Forecast analysis
Ming Li, Hefei Wang, Hua Fang. The Empirical Analysis and Prediction of China's FinTech Index Based on GARCH Model and BP Neural Network Model. Academic Journal of Business & Management (2021) Vol. 3, Issue 10: 119-126. https://doi.org/10.25236/AJBM.2021.031020.
[1] Bian Wanli (2021-11-04). The New development pattern of sustainable financial Development and high-quality service driven by fintech innovation. 21st Century Business Herald,007.
[2] Xiong Bin & Zhao Chun.(2021). Risk spillover effect of fintech on financial institutions: Based on GARCH-EVT-Copula-Covar model. Technology and Industry (10),29-37. doi:CNKI:SUN:CYYK.0.2021-10-006.
[3] Xiao xiang, Ding Yangyang & Wang Sichun.(2021). International Comparative study on fintech development Index. Financial Theory and Practice (10),12-21. doi:
[4] Zhang Rumeng & Zhang Huamei.(2021). Comparative analysis of BP neural network and ARMA-GARCH model in stock forecasting. Science Journal of Normal Universities (05) 14-20. doi:CNKI:SUN:GLKX.0.2021-05-004.
[5] Wei Liang, Yaqing Li, Xishou Huang & Hongjiao Li.(2020). Prediction of O_3 concentration in Nanning city based on ARMA-GARCH model. Guangxi science (01), 91-97. doi:10.13656/j.cnki.gxkx.20200311.011.
[6] Song HUA & Hu Taowen.(2021). Risk measurement of interest rate market based on ARMA-GARCH model. Journal of Yibin University (07),39-45. doi:10.19504/j.cnki.issn1671-5365.2021.07.005.
[7] Chen Cang & Zhao Zhiqin. (2021). Study on the volatility of Shanghai and Shenzhen 300 index based on GARCH family model. National circulation economy (15),110-112. doi:10.16834/j.cnki.issn1009-5292.2021.15.035.