Advances in Economics, Management and Political Sciences
- The Open Access Proceedings Series for Conferences
Series Vol. 40 , 10 November 2023
* Author to whom correspondence should be addressed.
Fluctuations in the stock market represent the changes in the national economy objectively, stock price prediction predicts the future trend of stocks using the past data, which has been widely focused on. Some machine learning algorithms, such as linear fitting and sequence mining, are used to predict the stock market. However, linear fitting faces the problem of overfitting and black relationships with historical data, while sequence mining is short in efficiency and lacks dynamic adaptations. State-of-the-art methods using attention mechanism in neural networks have shown exceptional performance targeting sequential prediction and classification. In this paper, we propose a combined LSTM-CNN attention model to explore the role of attention mechanism in Long Short-Term Memory (LSTM) network-based stock price movement prediction. Experimental results show that our LSTM-CNN-attention model can provide an accurate prediction and reliable trial on the stock price prediction, and the attention mechanism significantly improves the model performance in the stock market.
stock, time-series forecast, machine learning, attention mechanism
1. Hyndman, R. J., & Ord, J. K. (2006). Twenty-five years of forecasting. International Journal of Forecasting, 22(3), 413 - 414.
2. Tingting, Z., H. Yajie, Y. Mengnan, R. Dehua, C. Yarui, W.Yuan, & L. Jianzheng (2021). Research review of time series data prediction method based on machine learning. Journal of Tianjin University of Science and Technology 36(5), page 9. 255
3. White (1988). Economic prediction using neural networks: the case of IBM daily stock returns. In: IEEE 1988 International Conference on Neural Networks, 451–458 vol.2.doi: 10.1109/ICNN.1988.23959.
4. Tianyu, L., D. Laina, W. Haiyuan, W. Yinqiu, T. Mingwan, & Z. Xuewu (2019). Prediction of stock price trend based on principal component analysis and neural network combination. Computer Knowledge and Technology: Academic Edition (2X), 4, 250.
5. Li, F. (2014). Research on Prediction Model of Stock Price 240 Based on LM-BP Neural Network. Proceedings of the International Conference on Logistics, Engineering, Management and Computer Science, Atlantis Press, pages 776–778.
6. Yiran, G. , & W. Xiuli (2019). Rotation prediction of stock 260 market size and cap style based on BP neural network. computer simulation, 36(3).
7. Sepp Hochreiter, & Jürgen Schmidhuber (1997). Long Short-Term Memory. Neural Comput, 9 (8), 1735–1780. doi: 10.1162/neco.1997.9.8.1735.
8. Taghavi Namin, S., Esmaeilzadeh, M., Najafi, M. et al. (2018). Deep phenotyping: deep learning for temporal phenotype/genotype classification. Plant Methods, 14, 66.
9. Bai, S., Kolter, J. Z., & Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271.
10. Jie, Shen, Samuel, Albanie, Gang, Sun, and Enhua (2019). 235“Squeeze-and-Excitation Networks.” IEEE transactions on pattern analysis and machine intelligence.
11. Mohammed Ali Alshara (2022). Stock Forecasting Using Prophet vs. LSTM Model Applying Time-Series Prediction. IJCSNS, VOL.22 No.2.
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. Authors who publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open Access Instruction).