A hybrid model for stock price prediction based on multi-view heterogeneous data
Abstract Literature shows that both market data and financial media impact stock prices; however, using only one kind of data may lead to information bias. Therefore, this study uses market data and news to investigate their joint impact on stock price trends. However, combining these two types of i...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-02-01
|
| Series: | Financial Innovation |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40854-023-00519-w |
| _version_ | 1827326428820013056 |
|---|---|
| author | Wen Long Jing Gao Kehan Bai Zhichen Lu |
| author_facet | Wen Long Jing Gao Kehan Bai Zhichen Lu |
| author_sort | Wen Long |
| collection | DOAJ |
| description | Abstract Literature shows that both market data and financial media impact stock prices; however, using only one kind of data may lead to information bias. Therefore, this study uses market data and news to investigate their joint impact on stock price trends. However, combining these two types of information is difficult because of their completely different characteristics. This study develops a hybrid model called MVL-SVM for stock price trend prediction by integrating multi-view learning with a support vector machine (SVM). It works by simply inputting heterogeneous multi-view data simultaneously, which may reduce information loss. Compared with the ARIMA and classic SVM models based on single- and multi-view data, our hybrid model shows statistically significant advantages. In the robustness test, our model outperforms the others by at least 10% accuracy when the sliding windows of news and market data are set to 1–5 days, which confirms our model’s effectiveness. Finally, trading strategies based on single stock and investment portfolios are constructed separately, and the simulations show that MVL-SVM has better profitability and risk control performance than the benchmarks. |
| first_indexed | 2024-03-07T14:45:24Z |
| format | Article |
| id | doaj.art-235b2243f8984b7d95428e74b79ad37b |
| institution | Directory Open Access Journal |
| issn | 2199-4730 |
| language | English |
| last_indexed | 2024-03-07T14:45:24Z |
| publishDate | 2024-02-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Financial Innovation |
| spelling | doaj.art-235b2243f8984b7d95428e74b79ad37b2024-03-05T20:01:49ZengSpringerOpenFinancial Innovation2199-47302024-02-0110115010.1186/s40854-023-00519-wA hybrid model for stock price prediction based on multi-view heterogeneous dataWen Long0Jing Gao1Kehan Bai2Zhichen Lu3School of Economics and Management, University of Chinese Academy of SciencesSchool of Economics and Management, University of Chinese Academy of SciencesDepartment of Mathematics, Beijing Jiaotong UniversitySchool of Economics and Management, University of Chinese Academy of SciencesAbstract Literature shows that both market data and financial media impact stock prices; however, using only one kind of data may lead to information bias. Therefore, this study uses market data and news to investigate their joint impact on stock price trends. However, combining these two types of information is difficult because of their completely different characteristics. This study develops a hybrid model called MVL-SVM for stock price trend prediction by integrating multi-view learning with a support vector machine (SVM). It works by simply inputting heterogeneous multi-view data simultaneously, which may reduce information loss. Compared with the ARIMA and classic SVM models based on single- and multi-view data, our hybrid model shows statistically significant advantages. In the robustness test, our model outperforms the others by at least 10% accuracy when the sliding windows of news and market data are set to 1–5 days, which confirms our model’s effectiveness. Finally, trading strategies based on single stock and investment portfolios are constructed separately, and the simulations show that MVL-SVM has better profitability and risk control performance than the benchmarks.https://doi.org/10.1186/s40854-023-00519-wMarket dataFinancial newsSupport vector machineMulti-view learningHeterogeneous data |
| spellingShingle | Wen Long Jing Gao Kehan Bai Zhichen Lu A hybrid model for stock price prediction based on multi-view heterogeneous data Financial Innovation Market data Financial news Support vector machine Multi-view learning Heterogeneous data |
| title | A hybrid model for stock price prediction based on multi-view heterogeneous data |
| title_full | A hybrid model for stock price prediction based on multi-view heterogeneous data |
| title_fullStr | A hybrid model for stock price prediction based on multi-view heterogeneous data |
| title_full_unstemmed | A hybrid model for stock price prediction based on multi-view heterogeneous data |
| title_short | A hybrid model for stock price prediction based on multi-view heterogeneous data |
| title_sort | hybrid model for stock price prediction based on multi view heterogeneous data |
| topic | Market data Financial news Support vector machine Multi-view learning Heterogeneous data |
| url | https://doi.org/10.1186/s40854-023-00519-w |
| work_keys_str_mv | AT wenlong ahybridmodelforstockpricepredictionbasedonmultiviewheterogeneousdata AT jinggao ahybridmodelforstockpricepredictionbasedonmultiviewheterogeneousdata AT kehanbai ahybridmodelforstockpricepredictionbasedonmultiviewheterogeneousdata AT zhichenlu ahybridmodelforstockpricepredictionbasedonmultiviewheterogeneousdata AT wenlong hybridmodelforstockpricepredictionbasedonmultiviewheterogeneousdata AT jinggao hybridmodelforstockpricepredictionbasedonmultiviewheterogeneousdata AT kehanbai hybridmodelforstockpricepredictionbasedonmultiviewheterogeneousdata AT zhichenlu hybridmodelforstockpricepredictionbasedonmultiviewheterogeneousdata |