Stock movement prediction model based on gated orthogonal recurrent units
Stock movement prediction has received growing interest in the deep learning community. However, the generalization ability of some existing prediction models is weak due to the highly stochastic property of stock market, and some models suffer from the problem of gradient explosion or gradient vani...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | Intelligent Systems with Applications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S266730532200093X |
| _version_ | 1811211255291052032 |
|---|---|
| author | Jielin Leng Wei Liu Qiang Guo |
| author_facet | Jielin Leng Wei Liu Qiang Guo |
| author_sort | Jielin Leng |
| collection | DOAJ |
| description | Stock movement prediction has received growing interest in the deep learning community. However, the generalization ability of some existing prediction models is weak due to the highly stochastic property of stock market, and some models suffer from the problem of gradient explosion or gradient vanishing in the training process. To solve the above issues, in this paper, we propose a novel stock movement prediction model based on gated orthogonal recurrent units (GORU) and variational auto-encoder (VAE). Specifically, GORU encodes the text information, and then VAE infers and decodes the market information formed by concatenating encoded text information with normalized historical price information. Meanwhile, orthogonality introduced by GORU can alleviate the problem of gradient explosion or gradient vanishing and enhance the generalization ability of the model. We evaluate the relative contributions of text information and historical prices with respect to prediction accuracy by the results of an ablation study. The experimental results on publicly available datasets show that the proposed model is better than several state-of-the-art models, which indicates that the GORU and VAE can effectively improve the model's generalization ability and accuracy for predicting stock trends. |
| first_indexed | 2024-04-12T05:10:53Z |
| format | Article |
| id | doaj.art-da1c8bffa294442f8a13c49ee0b948c0 |
| institution | Directory Open Access Journal |
| issn | 2667-3053 |
| language | English |
| last_indexed | 2024-04-12T05:10:53Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Intelligent Systems with Applications |
| spelling | doaj.art-da1c8bffa294442f8a13c49ee0b948c02022-12-22T03:46:46ZengElsevierIntelligent Systems with Applications2667-30532022-11-0116200156Stock movement prediction model based on gated orthogonal recurrent unitsJielin Leng0Wei Liu1Qiang Guo2School of Computer Science and Technology, Shandong University of Finance and Economics, Jinan, 250014, ChinaSchool of Business Administration, Shandong University of Finance and Economics, Jinan, 250014, ChinaSchool of Computer Science and Technology, Shandong University of Finance and Economics, Jinan, 250014, China; Shandong Provincial Laboratory of Future Intelligence and Financial Engineering, Yantai, 264005, China; Corresponding author at: School of Computer Science and Technology, Shandong University of Finance and Economics, Jinan, 250014, China.Stock movement prediction has received growing interest in the deep learning community. However, the generalization ability of some existing prediction models is weak due to the highly stochastic property of stock market, and some models suffer from the problem of gradient explosion or gradient vanishing in the training process. To solve the above issues, in this paper, we propose a novel stock movement prediction model based on gated orthogonal recurrent units (GORU) and variational auto-encoder (VAE). Specifically, GORU encodes the text information, and then VAE infers and decodes the market information formed by concatenating encoded text information with normalized historical price information. Meanwhile, orthogonality introduced by GORU can alleviate the problem of gradient explosion or gradient vanishing and enhance the generalization ability of the model. We evaluate the relative contributions of text information and historical prices with respect to prediction accuracy by the results of an ablation study. The experimental results on publicly available datasets show that the proposed model is better than several state-of-the-art models, which indicates that the GORU and VAE can effectively improve the model's generalization ability and accuracy for predicting stock trends.http://www.sciencedirect.com/science/article/pii/S266730532200093XStock movement predictionDeep neural networkGated orthogonal recurrent unitText information encodingVariational inference |
| spellingShingle | Jielin Leng Wei Liu Qiang Guo Stock movement prediction model based on gated orthogonal recurrent units Intelligent Systems with Applications Stock movement prediction Deep neural network Gated orthogonal recurrent unit Text information encoding Variational inference |
| title | Stock movement prediction model based on gated orthogonal recurrent units |
| title_full | Stock movement prediction model based on gated orthogonal recurrent units |
| title_fullStr | Stock movement prediction model based on gated orthogonal recurrent units |
| title_full_unstemmed | Stock movement prediction model based on gated orthogonal recurrent units |
| title_short | Stock movement prediction model based on gated orthogonal recurrent units |
| title_sort | stock movement prediction model based on gated orthogonal recurrent units |
| topic | Stock movement prediction Deep neural network Gated orthogonal recurrent unit Text information encoding Variational inference |
| url | http://www.sciencedirect.com/science/article/pii/S266730532200093X |
| work_keys_str_mv | AT jielinleng stockmovementpredictionmodelbasedongatedorthogonalrecurrentunits AT weiliu stockmovementpredictionmodelbasedongatedorthogonalrecurrentunits AT qiangguo stockmovementpredictionmodelbasedongatedorthogonalrecurrentunits |