Trend and Volatility Analysis of Shanghai Composite Index Returns Based on ARMA and LSTM Model

Wenting  Ma

doi:10.6180/jase.202603_29(3).0010

Trend and Volatility Analysis of Shanghai Composite Index Returns Based on ARMA and LSTM Model

Research Categories

Wenting MaThis email address is being protected from spambots. You need JavaScript enabled to view it.

School of Finance and Economics, Zhengzhou University of Science and Technology, Zhengzhou 450064 China

Received: May 12, 2025
Accepted: June 13, 2025
Publication Date: June 28, 2025

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202603_29(3).0010

This paper takes the daily return rate of the Shanghai Composite Index as a sample to establish the ARMA-LSTM (Long Short-Term Memory) model for the Shanghai Composite Index. It compares the fitting effect of ARMA model on the volatility of the Shanghai Composite Index under different distribution assumptions, calculates and tests the coverage of the prediction results of the Value-at-Risk (VaR) value of the Shanghai Composite Index on the actual losses. The analysis results show that the ARMA model is more suitable for measuring the conditional variance of the Shanghai Composite Index. With the t-distribution, the model can better reflect the distribution characteristics of the perturbation term of the Shanghai Composite Index’s return rate. Furthermore, in order to overcome the large errors that occur in the medium and long-term prediction of the ARMA model, the ARMA model combined with the LSTM model is used to predict the exponential volatility, effectively improving the prediction accuracy of the ARMA-LSTM model. Finally, through the ARMA model, the impact of the full implementation of the registration system in China’s stock market on the volatility of the Shanghai Composite Index is preliminarily examined. It is found that the implementation of this policy significantly reduces the fluctuation range of the Shanghai Composite Index.

Keywords: Shanghai Composite Index, Value-at-Risk, ARMA-LSTM model, registration system

[1] M. B. Devereux and C. Yu, (2020) “International financial integration and crisis contagion" The Review of Economic Studies 87(3): 1174–1212. DOI: http: //mcej.modares.ac.ir/article-16-7658-en.html.
[2] A. A. Syed, (2025) “Assessing the role of global and regional economic integration on financial inclusion among BRICS economies" Journal of Financial Economic Pol icy: DOI: 10.1108/JFEP-08-2024-0236.
[3] E. G. Mendoza, V. Quadrini, and J.-V. Rios-Rull, (2009) “Financial integration, financial development, and global imbalances" Journal of Political economy 117(3): 371–416. DOI: 10.1086/599706.
[4] I. Mork¯ unait˙ e, D. Celov, and R. Leipus, (2024) “Evaluation of Value-at-Risk (VaR) using the Gaussian Mixture Models" Research in Statistics 2(1): 2346075. DOI: 10.1080/27684520.2024.2346075.
[5] F. M. Müller and M. B. Righi, (2024) “Comparison of value at risk (VaR) multivariate forecast models" Computational economics 63(1): 75–110. DOI: 10.1007/s10614-022-10330-x.
[6] S. Yin, H. Li, A. A. Laghari, L. Teng, T. R. Gadekallu, and A. Almadhor, (2024) “FLSN-MVO: Edge Comput ing and Privacy Protection Based on Federated Learning Siamese Network With Multi-Verse Optimization Algorithm for Industry 5.0" IEEE Open Journal of the Communications Society 6: DOI: 10.1109/OJCOMS. 2024.3520562.
[7] Y. He, C. Zhu, and C. Cao, (2024) “A wind power ramp prediction method based on value-at-risk" Energy Conversion and Management 315: 118767. DOI: 10.1016/j.enconman.2024.118767.
[8] K. Syuhada, R. Puspitasari, I. K. D. Arnawa, L. Mufaridho, E. Elonasari, M. Jannah, and A. Rohmawati, (2024) “Enhancing Value-at-Risk with Credible Expected Risk Models" International Journal of Financial Studies 12(3): 80. DOI: 10.3390/ijfs12030080.
[9] S. M. Shariff, (2022) “Autoregressive integrated moving average (ARIMA) and long short-term memory (LSTM) network models for forecasting energy consumptions" European Journal of Electrical Engineering and Computer Science 6(3): 7–10. DOI: 10.24018/ejece.2022.6. 3.435.
[10] Z. S. Khozani, F. B. Banadkooki, M. Ehteram, A. N. Ahmed, and A. El-Shafie, (2022) “Combining autore gressive integrated moving average with Long Short-Term Memory neural network and optimisation algorithms for predicting ground water level" Journal of Cleaner Pro duction 348: 131224. DOI: 10.1016/j.jclepro.2022. 131224.
[11] H. Cao, Y. Li, W. Chen, J. Chen, etal., (2017) “Systemic risk in China’s interbank lending market" Journal of Mathematical Finance 7(01): 188. DOI: 10.4236/jmf.2017.71010.
[12] G.-J. Wang, C. Xie, Z.-Q. Jiang, and H. E. Stanley, (2016) “Extreme risk spillover effects in world gold markets and the global financial crisis" International Re view of Economics & Finance 46: 55–77. DOI: 10. 1016/j.iref.2016.08.004.
[13] D. Ardia, K. Bluteau, K. Boudt, L. Catania, and D.-A. Trottier, (2019) “Markov-switching GARCH models in R: The MSGARCH package" Journal of Statistical Software 91: 1–38. DOI: 10.18637/jss.v091.i04.
[14] S. Chen, B. Zhang, and J. Deng, (2018) “Research on Risk Measurement in Financial Market Based on GARCH VaR and FHS——An Example of Chinese Bond Market" Applied Economics and Finance 5(4): 102–116. DOI: 10.11114/aef.v5i4.3307.
[15] S.-S. Lin, (2014) “Investigation of forecasted risk inter relationship: base on GARCH model, causality in China markets" Journal of Business Economics and Management 15(5): 853–861. DOI: 10.3846/16111699.2013.839474.
[16] I. D. Ratih, B. S. S. Ulama, and M. Prastuti. “Value-at Risk analysis using ARMAX GARCHX approach for estimating risk of banking subsector stock return’s”. In: Journal of Physics: Conference Series. 974. 1. IOP Publishing. 2018, 012029. DOI: 10.1088/1742-6596/974/1/012029.
[17] I. Yousaf, M. Youssef, and M. Gubareva. “Return and Volatility Spillovers Between Non-fungible To kens and Conventional Currencies: Evidence from the TVP–VAR Model”. In: Blockchain, Crypto Assets, and Financial Innovation. Springer, 2025, 326–351. DOI: 10.1007/978-981-96-6839-7_12.
[18] J. Anttonen, M. Lanne, and J. Luoto, (2024) “Statistically identified structural VAR model with potentially skewed and fat-tailed errors" Journal of Applied Econometrics 39(3): 422–437. DOI: 10.1002/jae.3019.
[19] J. Yu, L. Zhao, S. Yin, and M. Ivanovi´ c, (2024) “News recommendation model based on encoder graph neural network and bat optimization in online social multimedia art education" Computer Science and Information Systems 21(3): 989–1012. DOI: 10.2298/CSIS231225025Y.
[20] A. Jisi, S. Yin, et al., (2021) “A new feature fusion network for student behavior recognition in education" Journal of Applied Science and Engineering 24(2): 133 140. DOI: 10.6180/jase.202104_24(2).0002.
[21] W.-X. Ma and E. Fan,(2011) “Linear superposition principle applying to Hirota bilinear equations" Computers & Mathematics with Applications 61(4): 950–959. DOI: 10.1016/j.camwa.2010.12.043.
[22] S. Kim, J. Son, and B. Shim, (2021) “Energy-efficient ultra-dense network using LSTM-based deep neural networks" IEEE Transactions on Wireless Communications 20(7): 4702–4715. DOI: 10.1109/TWC.2021.3061577.

Latest Articles