A dual-path convolutional neural network combined with an attention-based bidirectional long short-term memory network for stock price prediction.
The complexities of stock price data, characterized by its nonlinearity, non-stationarity, and intricate spatiotemporal patterns, make accurate prediction a substantial challenge. To address this, we propose the DCA-BiLSTM model, which combines dual-path convolutional neural networks with an attenti...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0319775 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849711275572985856 |
|---|---|
| author | Guiyan Zhao Yunfei Cheng Jianhui Yang Jiayuan Ouyang |
| author_facet | Guiyan Zhao Yunfei Cheng Jianhui Yang Jiayuan Ouyang |
| author_sort | Guiyan Zhao |
| collection | DOAJ |
| description | The complexities of stock price data, characterized by its nonlinearity, non-stationarity, and intricate spatiotemporal patterns, make accurate prediction a substantial challenge. To address this, we propose the DCA-BiLSTM model, which combines dual-path convolutional neural networks with an attention mechanism (DCA) and bidirectional long short-term memory networks (BiLSTM). This model captures deep information and complex dependencies within time-series data. First, wavelet packet decomposition extracts high- and low-frequency features, followed by DCA for robust deep feature extraction, and finally, BiLSTM models bidirectional dependencies. Validated on datasets from Yahoo Finance, including Apple, Google, Tesla stocks, and the Nasdaq index, the model consistently outperforms traditional approaches. The DCA-BiLSTM achieves an [Formula: see text] of 0.9507 for Apple, 0.9595 for Google, 0.9077 for Tesla, and 0.9594 for the Nasdaq index, with significant reductions in error metrics across all datasets. These results demonstrate the model's robustness and improved predictive accuracy, offering reliable insights for stock price forecasting. |
| format | Article |
| id | doaj-art-7c4af64cc36c41d5bc4aa5738b516305 |
| institution | DOAJ |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-7c4af64cc36c41d5bc4aa5738b5163052025-08-20T03:14:39ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01204e031977510.1371/journal.pone.0319775A dual-path convolutional neural network combined with an attention-based bidirectional long short-term memory network for stock price prediction.Guiyan ZhaoYunfei ChengJianhui YangJiayuan OuyangThe complexities of stock price data, characterized by its nonlinearity, non-stationarity, and intricate spatiotemporal patterns, make accurate prediction a substantial challenge. To address this, we propose the DCA-BiLSTM model, which combines dual-path convolutional neural networks with an attention mechanism (DCA) and bidirectional long short-term memory networks (BiLSTM). This model captures deep information and complex dependencies within time-series data. First, wavelet packet decomposition extracts high- and low-frequency features, followed by DCA for robust deep feature extraction, and finally, BiLSTM models bidirectional dependencies. Validated on datasets from Yahoo Finance, including Apple, Google, Tesla stocks, and the Nasdaq index, the model consistently outperforms traditional approaches. The DCA-BiLSTM achieves an [Formula: see text] of 0.9507 for Apple, 0.9595 for Google, 0.9077 for Tesla, and 0.9594 for the Nasdaq index, with significant reductions in error metrics across all datasets. These results demonstrate the model's robustness and improved predictive accuracy, offering reliable insights for stock price forecasting.https://doi.org/10.1371/journal.pone.0319775 |
| spellingShingle | Guiyan Zhao Yunfei Cheng Jianhui Yang Jiayuan Ouyang A dual-path convolutional neural network combined with an attention-based bidirectional long short-term memory network for stock price prediction. PLoS ONE |
| title | A dual-path convolutional neural network combined with an attention-based bidirectional long short-term memory network for stock price prediction. |
| title_full | A dual-path convolutional neural network combined with an attention-based bidirectional long short-term memory network for stock price prediction. |
| title_fullStr | A dual-path convolutional neural network combined with an attention-based bidirectional long short-term memory network for stock price prediction. |
| title_full_unstemmed | A dual-path convolutional neural network combined with an attention-based bidirectional long short-term memory network for stock price prediction. |
| title_short | A dual-path convolutional neural network combined with an attention-based bidirectional long short-term memory network for stock price prediction. |
| title_sort | dual path convolutional neural network combined with an attention based bidirectional long short term memory network for stock price prediction |
| url | https://doi.org/10.1371/journal.pone.0319775 |
| work_keys_str_mv | AT guiyanzhao adualpathconvolutionalneuralnetworkcombinedwithanattentionbasedbidirectionallongshorttermmemorynetworkforstockpriceprediction AT yunfeicheng adualpathconvolutionalneuralnetworkcombinedwithanattentionbasedbidirectionallongshorttermmemorynetworkforstockpriceprediction AT jianhuiyang adualpathconvolutionalneuralnetworkcombinedwithanattentionbasedbidirectionallongshorttermmemorynetworkforstockpriceprediction AT jiayuanouyang adualpathconvolutionalneuralnetworkcombinedwithanattentionbasedbidirectionallongshorttermmemorynetworkforstockpriceprediction AT guiyanzhao dualpathconvolutionalneuralnetworkcombinedwithanattentionbasedbidirectionallongshorttermmemorynetworkforstockpriceprediction AT yunfeicheng dualpathconvolutionalneuralnetworkcombinedwithanattentionbasedbidirectionallongshorttermmemorynetworkforstockpriceprediction AT jianhuiyang dualpathconvolutionalneuralnetworkcombinedwithanattentionbasedbidirectionallongshorttermmemorynetworkforstockpriceprediction AT jiayuanouyang dualpathconvolutionalneuralnetworkcombinedwithanattentionbasedbidirectionallongshorttermmemorynetworkforstockpriceprediction |