Abstract
Stock price prediction is a crucial task in quantitative trading. The recent advancements in deep learning have sparked interest in using neural networks to identify stock market patterns. However, existing deep learning models have limitations in exploring long dependencies in time-series data and capturing local features, making it challenging to reflect the impact of feature factors on stock prices. To address this, we propose a convolutional attention mechanism-based stock price prediction model, StPrformer. The model utilizes a convolutional attention mechanism to mine temporal dependencies between stock prices and feature factors. Additionally, the convolutional layer in the encoder provides direct a priori information of input features for prediction. Our experiments demonstrate that StPrformer outperforms existing deep learning models in terms of prediction accuracy. Compared to the classical Transformer prediction model, StPrformer reduces the average absolute error and mean square error by 33.3% and 26.1%, respectively. These results confirm the universality and superiority of StPrformer.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gurland, J., Whittle, P.: Hypothesis testing in time series analysis. J. Am. Stat. Assoc. 49(1), 197–201 (1954)
Box, G., Jenkins, G.: Time series analysis forecasting and control. J. Time 31(4), 238–242 (1976)
Adebiyi, A., Adewumi, A., Ayo, K.: Stock price prediction using the ARIMA model. In: UKSim-AMSS 16th International Conference on Computer Modelling and Simulation, pp. 106–112. IEEE (2014)
Fischer, T., Krauss, C.: Deep learning with long short-term memory networks for financial market predictions. Eur. J. Oper. Res. 2(3), 45–48 (2017)
Selvin, S., Sreelekshmy, A.: Stock price prediction using LSTM, RNN and CNN-sliding window model. In: International Conference on Advances in Computing, vol. 13, no. 21, pp. 453-456. IEEE (2017)
Zhou, X., Pan, Z., Hu, G., et al.: Stock market prediction on high-frequency data using generative adversarial nets. Math. Probl. Eng. 11(3), 20–24 (2018)
Zhang, X., Ying, T.: deep stock ranker: a LSTM neural network model for stock selection. In: DMBD, pp. 654–657 (2018)
Zhang, Q.Y., Qin, C., Zhang, F.Y., et al.: Transformer-based attention network for stock movement prediction. Expert Syst. Appl. 202, 117239 (2022)
Wang, C.J., Chen, Y.Y., Zhang, S.Q., et al.: Stock market index prediction using deep Transformer model. Expert Syst. Appl. 208, 118128 (2022)
Ding, Q.G., Wu, S.F., Sun, H., et al.: Hierarchical multi-scale Gaussian transformer for stock movement prediction. In: International Joint Conference on Artificial Intelligence, pp. 4640–4646 (2022)
Gu, L.Q., Wu, Y.J., Pang, J.H.: GRU based on attention mechanism stock forecast model. Syst. Eng. 38(5), 134–140 (2020)
Yang, L., Yao, R.J.: Research on credit card default prediction model based on transformer. Comput. Simul. 38(8), 440–444 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, Z., Zhang, Q., Huang, D., Wu, D. (2023). StPrformer: A Stock Price Prediction Model Based on Convolutional Attention Mechanism. In: Huang, DS., Premaratne, P., Jin, B., Qu, B., Jo, KH., Hussain, A. (eds) Advanced Intelligent Computing Technology and Applications. ICIC 2023. Lecture Notes in Computer Science(), vol 14090. Springer, Singapore. https://doi.org/10.1007/978-981-99-4761-4_37
Download citation
DOI: https://doi.org/10.1007/978-981-99-4761-4_37
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-4760-7
Online ISBN: 978-981-99-4761-4
eBook Packages: Computer ScienceComputer Science (R0)