Trend Prediction Analysis of Shanghai Composite Index Based on LSTM Neural Network
DOI:
https://doi.org/10.54097/qw8hwy64Keywords:
LSTM Model, Shanghai Composite Index, ForecastsAbstract
The prediction of stock indices, particularly the Shanghai Composite Index (SCI), is crucial for understanding the health and direction of China's financial market in the post-pandemic era. Given the challenges of traditional forecasting methods due to the unpredictable nature of stock prices, this study explores the application of the Long Short-Term Memory (LSTM) neural network, complemented by Monte Carlo simulations and regularization with the daily trading data from September 21 2020, to August 13, 2023, to forecast the SCI's price trends for Q4 2023. The findings suggest a trajectory characterized by an initial decline, succeeded by a steady upward trend throughout the entirety of the quarter. Notably, the results have adeptly encapsulated both the lingering effects of the pandemic and the long-term rising trend of the Shanghai Composite Index (SCI). This research accentuates the potential of advanced neural network models in deciphering complex stock market behaviors, offering a groundbreaking perspective for market participants in navigating future investment decisions.
Downloads
References
Li Min, Zou Jiezhong, Li Junping, Liang Jianwu. Prediction of Shenzhen and Shanghai stock markets using ARMA model. Journal of Changsha Railway Institute, 2000(01): 78-84.
Feng Pan, Cao Xianbing. Empirical research on stock price analysis and prediction based on ARMA model. Mathematics in Practice and Understanding, 2011, 41(22): 84-90.
Matsuba, Ikuo. Application of neural sequential associator to long-term stock price prediction. IEEE International Joint Conference on Neural Networks. IEEE, 1991: 1476-1479.
Kimoto T, Asakawa K, Yoda M, et al. Stock market prediction system with modular neural networks. Neural Networks, 1990., 1990 IJCNN International Joint Conference on. IEEE 1990: 1-6 vol.1.
G. Peter Zhang. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 2003(50): 159-175.
Y. Bengio, P. Simard and P. Frasconi. Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, vol. 5, no. 2, pp. 157-166, March 1994.
Hochreiter S, Schmidhuber J. Long Short-Term Memory. Neural Computation, 1997, 9(8): 1735-1780.
Li Jie, Lin Yongfeng. Time-series data prediction based on multi-time scale RNN. Computer Applications and Software, 2018, 35(7): 33-37.
Chen K, Zhou Y, Dai F. A LSTM-based method for stock returns prediction: A case study of China stock market. IEEE International Conference on Big Data. IEEE, 2015: 2823-2824.
Xu Hong, & Pu Hongxia. The impact of the COVID-19 pandemic on China's stock market: A study based on the event research method. Financial Forum, 2021, 26(7): 11.
Chen Lin, & Qu Xiaohui. Market reaction to infectious public health events: A study on the impact of the COVID-19 epidemic on China's stock market. Financial Forum, 2020, 25(7): 10.
The People's Bank of China. The People's Bank of China announces the decision to reduce the reserve requirement ratio for financial institutions on March 27, 2023. URL: http://www.pbc.gov.cn/goutongjiaoliu/113456/113469/4821841/index.html , last accessed 2023/8/27.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
