Sector influence aware stock trend prediction using 3D convolutional neural network
Stock price prediction is a difficult task. This article takes on this challenge and proposes a 3D Convolutional Neural Network based approach to classify the directional trends in a stock’s price. To do that, five companies from a sector are grouped together, and the overall trend in each is predic...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-04-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157822000416 |
| _version_ | 1828134434024456192 |
|---|---|
| author | Siddhant Sinha Shambhavi Mishra Vipul Mishra Tanveer Ahmed |
| author_facet | Siddhant Sinha Shambhavi Mishra Vipul Mishra Tanveer Ahmed |
| author_sort | Siddhant Sinha |
| collection | DOAJ |
| description | Stock price prediction is a difficult task. This article takes on this challenge and proposes a 3D Convolutional Neural Network based approach to classify the directional trends in a stock’s price. To do that, five companies from a sector are grouped together, and the overall trend in each is predicted simultaneously. This is done to analyze the influence of one company on another. For each company, multiple technical indicators are chosen, and the stock prices are converted into a 3D image of size 15×15×5. To find the best features, we experiment with hierarchical clustering. To complement the 3D Convolutional Neural Network, we also examine the idea of ensemble learning. The proposed method and several existing models are combined to improve the performance of the system. Experimentation is performed on forty-five different companies of the National Stock Exchange. Compared to other similar techniques in literature, our work has achieved up to 35% annual returns for some stocks, with the average being 9.19%. Lastly, we also try to show that grouping companies together and making the prediction on a sector could serve as a new benchmark for stock trend classification. |
| first_indexed | 2024-04-11T17:34:15Z |
| format | Article |
| id | doaj.art-336a5410a4d44e308b14d1a4fc2d1b68 |
| institution | Directory Open Access Journal |
| issn | 1319-1578 |
| language | English |
| last_indexed | 2024-04-11T17:34:15Z |
| publishDate | 2022-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj.art-336a5410a4d44e308b14d1a4fc2d1b682022-12-22T04:11:39ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782022-04-0134415111522Sector influence aware stock trend prediction using 3D convolutional neural networkSiddhant Sinha0Shambhavi Mishra1Vipul Mishra2Tanveer Ahmed3Manipal Institute of Technology, Manipal, Karnataka, IndiaBennett University, Greater Noida, Uttar Pradesh, 201310, IndiaBennett University, Greater Noida, Uttar Pradesh, 201310, India; Corresponding author.Bennett University, Greater Noida, Uttar Pradesh, 201310, IndiaStock price prediction is a difficult task. This article takes on this challenge and proposes a 3D Convolutional Neural Network based approach to classify the directional trends in a stock’s price. To do that, five companies from a sector are grouped together, and the overall trend in each is predicted simultaneously. This is done to analyze the influence of one company on another. For each company, multiple technical indicators are chosen, and the stock prices are converted into a 3D image of size 15×15×5. To find the best features, we experiment with hierarchical clustering. To complement the 3D Convolutional Neural Network, we also examine the idea of ensemble learning. The proposed method and several existing models are combined to improve the performance of the system. Experimentation is performed on forty-five different companies of the National Stock Exchange. Compared to other similar techniques in literature, our work has achieved up to 35% annual returns for some stocks, with the average being 9.19%. Lastly, we also try to show that grouping companies together and making the prediction on a sector could serve as a new benchmark for stock trend classification.http://www.sciencedirect.com/science/article/pii/S1319157822000416Stock trend classificationDeep learningTradingConvolutional neural networkTechnical indicatorsEnsemble learning |
| spellingShingle | Siddhant Sinha Shambhavi Mishra Vipul Mishra Tanveer Ahmed Sector influence aware stock trend prediction using 3D convolutional neural network Journal of King Saud University: Computer and Information Sciences Stock trend classification Deep learning Trading Convolutional neural network Technical indicators Ensemble learning |
| title | Sector influence aware stock trend prediction using 3D convolutional neural network |
| title_full | Sector influence aware stock trend prediction using 3D convolutional neural network |
| title_fullStr | Sector influence aware stock trend prediction using 3D convolutional neural network |
| title_full_unstemmed | Sector influence aware stock trend prediction using 3D convolutional neural network |
| title_short | Sector influence aware stock trend prediction using 3D convolutional neural network |
| title_sort | sector influence aware stock trend prediction using 3d convolutional neural network |
| topic | Stock trend classification Deep learning Trading Convolutional neural network Technical indicators Ensemble learning |
| url | http://www.sciencedirect.com/science/article/pii/S1319157822000416 |
| work_keys_str_mv | AT siddhantsinha sectorinfluenceawarestocktrendpredictionusing3dconvolutionalneuralnetwork AT shambhavimishra sectorinfluenceawarestocktrendpredictionusing3dconvolutionalneuralnetwork AT vipulmishra sectorinfluenceawarestocktrendpredictionusing3dconvolutionalneuralnetwork AT tanveerahmed sectorinfluenceawarestocktrendpredictionusing3dconvolutionalneuralnetwork |