A Stock Prediction Method Based on Heterogeneous Bidirectional LSTM
Source abstract
Abstract
LSTM (long short-term memory) networks have been proven effective in processing stock data. However, the stability of LSTM is poor, it is greatly affected by data fluctuations, and it is weak in capturing long-term dependencies in sequential data. BiLSTM (bidirectional LSTM) has alleviated this issue to some extent; however, due to the inefficiency of information transmission within the LSTM units themselves, the generalization performance and accuracy of BiLSTM is still not very satisfactory. To address this problem, this paper improves LSTM units on the basis of traditional BiLSTM and proposes a He-BiLSTM (heterogeneous bidirectional LSTM) with a corresponding backpropagation algorithm. The parameters in He-BiLSTM are updated using the Adam gradient descent method. Experimental results show that compared to BiLSTM, He-BiLSTM has further improved in terms of accuracy, robustness, and generalization performance.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Stock Market Forecasting Methods · Energy Load and Power Forecasting · Forecasting Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Mathematics, Physics and Statistics, Shanghai University of Engineering Science, Shanghai 201620, China
Funding
National Natural Science Foundation of China · Shanghai University of Engineering Science Horizontal Research Project
References (26)
Show source-provided references
1. Surveying stock market forecasting techniques—Part II: Soft computing methods10.1016/j.eswa.2008.07.006 ↗
2. A hybrid approach by integrating wavelet based feature extraction with MARS and SVR for stock index forecasting10.1016/j.dss.2012.11.012 ↗
3. Does weather influence investor behavior, stock returns, and volatility? Evidence from the Greater China region10.1016/j.physa.2019.02.015 ↗
4. Predicting Trend of High Frequency CSI 300 Index Using Adaptive Input Selection and Machine Learning Techniques
5. The application research of neural network and BP algorithm in stock price pattern classification and prediction10.1016/j.future.2020.10.009 ↗
6. BP Neural Network Stock Price Prediction Based on Adaptive Firefly Algorithm
7. Kong, D.W., Liu, S.J., and Pan, L. (2021, January 5–7). Amazon Spot Instance Price Prediction with GRU Network. Proceedings of the IEEE International Conference on Computer Supported Cooperative Work in Design (CSCWD), Dalian, China.10.1109/CSCWD49262.2021.9437881 ↗
8. Prediction of SSE Shanghai Enterprises index based on bidirectional LSTM model of air pollutants10.1016/j.eswa.2022.117600 ↗
9. Robust speech emotion recognition using CNN+LSTM based on stochastic fractal search optimization algorithm10.1109/ACCESS.2022.3172954 ↗
10. Learning precise timing with LSTM recurrent networks
11. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
12. An integrated framework of Bi-directional Long-Short Term Memory (BiLSTM) based on sine cosine algorithm for hourly solar radiation forecasting10.1016/j.energy.2021.119887 ↗
13. A hybrid electricity price forecasting model with Bayesian optimization for German energy exchange10.1016/j.ijepes.2019.03.056 ↗
14. Bayesian BILSTM approach for tourism demand forecasting10.1016/j.annals.2020.102925 ↗
15. Abe, M., and Nakayama, H. (2018, January 3–6). Deep learning for forecasting stock returns in the cross section. Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining, Melbourne, VIC, Australia.10.1007/978-3-319-93034-3_22 ↗
16. Deep learning with long short-term memory networks for financial market predictions10.1016/j.ejor.2017.11.054 ↗
17. Decision support from financial disclosures with deep neural networks and transfer learning10.1016/j.dss.2017.10.001 ↗
18. Predicting equity Price with corporate action events using LSTMRNN10.4236/jmf.2018.81005 ↗
19. Choi, H.K. (2018). Stock price correlation coefficient prediction with ARIMA-LSTM hybrid model. arXiv.
20. Fan, Y., Qian, Y., Xie, F.L., and Soong, F.K. (2014, January 14–18). TTS synthesis with bidirectional LSTM based recurrent neural networks. Proceedings of the Fifteenth Annual Conference of the International Speech Communication Association, Singapore.10.21437/Interspeech.2014-443 ↗
21. Graves, A., Jaitly, N., and Mohamed, A.R. (2013, January 8–12). Hybrid speech recognition with deep bidirectional LSTM. Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013—Proceedings, Olomouc, Czech Republic.10.1109/ASRU.2013.6707742 ↗
22. Framewise phoneme classification with bidirectional LSTM and other neural network architectures10.1016/j.neunet.2005.06.042 ↗
23. Bidirectional recurrent neural networks10.1109/78.650093 ↗
24. Siami-Namini, S., Tavakoli, N., and Namin, A.S. (2019, January 9–12). The performance of LSTM and BiLSTM in forecasting time series. Proceedings of the 2019 IEEE International Conference on Big Data, Los Angeles, CA, USA.10.1109/BigData47090.2019.9005997 ↗
25. Learning to forget: Continual prediction with lstm10.1162/089976600300015015 ↗
26. Sang, S., and Li, L. (2024). A Novel Variant of LSTM Stock Prediction Method Incorporating Attention Mechanism. Mathematics, 12.10.3390/math12070945 ↗