Forecast and Analysis of the Fifth Trading Day Yield based on the Last 35 Trading days-Based on Long Short-Term Memory Methord

Yiyang Luo

doi:10.54097/623d4z05

Authors

Yiyang Luo Internet College, Anhui University, Hefei, 230000, China

DOI:

https://doi.org/10.54097/623d4z05

Keywords:

Lightweight, Double-Layer Long Short-Term Memory (LSTM) Architecture, CSI 300 Index, Logarithmic Return Rate.

Abstract

Throughout the past two decades, the China Securities Index 300 (CSI 300) Index has undergone a frequency of extreme fluctuations. This renders traditional prediction models unable to precisely capture its dynamic changes. The existing GARCH and VAR models can only partially illustrate the statistical traits of the CSI 300 Index. They cannot simultaneously account for the sharp peaks and heavy tails, long - term memory, and the 5 - day operation cycle generated by the T + 1 trading system exclusive to the A - share market. The lightweight Long - Short Term Memory prediction framework contrived in this study uses only a 35×5 OHLCV matrix as input, without bringing in external material. It gets rapid training via a basic double - layer Long Short-Term Memory (LSTM) (32, 16) - Dense (1) structure, aiming to provide a low - cost and useful prediction tool. The double - layer LSTM configured with 32 - 16 neurons gets an ideal balance in parameter quantity, training efficiency, and prediction accuracy.It confirms the principle of complexity - data scale consistency and guarantees the model functions smoothly and profitably.It validates the principle of complexity - data scale consistency and guarantees the model functions.

Downloads

Download data is not yet available.

References

[1] Banik, S., Sharma, N., Mangla, M., et al. (2022). LSTM based decision support system for swing trading in stock market. Knowledge-Based Systems, 239, 107994.

[2] Chen, Z. L., & Dong, H. S. (2023). Analysis of the trend and influencing factors of the Shanghai-Shenzhen 300 index from 2000 to 2019. Market China, (7), 1–12.

[3] Ding, G., & Qin, L. (2020). Study on the prediction of stock price based on the associated network model of LSTM. International Journal of Machine Learning and Cybernetics, 11(6), 1307–1317.

[4] Gao, Y., Wang, R., & Zhou, E. (2021). Stock prediction based on optimized LSTM and GRU models. Scientific Programming, 2021, 4055281.

[5] Geng, J., & Liu, Y. C. (2019). Analysis and prediction of stock returns based on GARCH model. Hebei Enterprise, (10), 61–62.

[6] Ghosh, P., Neufeld, A., & Sahoo, J. K. (2021). Forecasting directional movements of stock prices for intraday trading using LSTM and random forests. arXiv preprintarXiv:2004.10178v2.

[7] Gu, L., & Wang, X. (2022). Stock price forecasting research based on LSTM model: A case study of Poly Development. Advances in Social Sciences, 11(11), 4517–4527.

[8] Gu, W., Zhong, Y., Li, S., et al. (2024). Predicting stock prices with FinBERT-LSTM: Integrating news sentiment analysis. In 2024 8th International Conference on Cloud and Big Data Computing (ICCBDC 2024)(pp. 67–72).

[9] Gülmez, B. (2023). Stock price prediction with optimized deep LSTM network with artificial rabbits optimization algorithm. Expert Systems with Applications, 227, 120346.

[10] Han, C., & Fu, X. (2023). Challenge and opportunity: Deep learning-based stock price prediction by using bi-directional LSTM model. Frontiers in Business, Economics and Management, 8(2), 51–54.

[11] Li, J. Y. (2025). Empirical analysis and prediction of the return rate of the ChiNext index based on VAR model. Journal of Huaibei Normal University (Natural Science Edition), 46(2), 13–18.

[12] Liu, S. C. (2025). Analysis of stock price prediction methods based on LSTM machine learning model(Master’s thesis, Hangzhou Dianzi University).

[13] Luo, A., Zhong, L., Wang, J., et al. (2024). Short-term stock correlation forecasting based on CNN-BiLSTM enhanced by attention mechanism. IEEE Access, 12, 29617–29632.

[14] Mehtab, S., & Sen, J. (2020). Stock price prediction using CNN and LSTM-based deep learning models. Preprints, 2010.13891v1.

[15] Mehtab, S., Sen, J., & Dutta, A. (2020). Stock price prediction using machine learning and LSTM-based deep learning models. Preprints, 2009.10819v1.

[16] Qiao, R., Chen, W., & Qiao, Y. (2022). Prediction of stock return by LSTM neural network. Applied Artificial Intelligence, 36(1), 2151159.

[17] Zhao, Q., Hao, Y., & Li, X. (2024). Stock price prediction based on hybrid CNN-LSTM model. Preprints, 202409.1904.v1.

[18] Wu, J., Zhang, Y., & Liu, Z. (2025). Enhancing LSTM for financial time series prediction via improved cell structure. Journal of Computational Finance, 29(2), 45–68.