Integrated Long-Term Stock Selection Models Based on Feature Selection and Machine Learning Algorithms for China Stock Market
The classical linear multi-factor stock selection model is widely used for long-term stock price trend prediction. However, the stock market is chaotic, complex, and dynamic, for which reasons the linear model assumption may be unreasonable, and it is more meaningful to construct a better-integrated...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8968561/ |
| id |
doaj-dee93c49929948a5ace64fee9c7679ee |
|---|---|
| record_format |
Article |
| spelling |
doaj-dee93c49929948a5ace64fee9c7679ee2021-03-30T01:14:17ZengIEEEIEEE Access2169-35362020-01-018226722268510.1109/ACCESS.2020.29692938968561Integrated Long-Term Stock Selection Models Based on Feature Selection and Machine Learning Algorithms for China Stock MarketXianghui Yuan0Jin Yuan1https://orcid.org/0000-0001-6509-988XTianzhao Jiang2Qurat Ul Ain3School of Economics and Finance, Xi’an Jiaotong University, Xi’an, ChinaSchool of Economics and Finance, Xi’an Jiaotong University, Xi’an, ChinaShanghai Foresee Investment Ltd., Liability Company, Shanghai, ChinaSchool of Economics and Finance, Xi’an Jiaotong University, Xi’an, ChinaThe classical linear multi-factor stock selection model is widely used for long-term stock price trend prediction. However, the stock market is chaotic, complex, and dynamic, for which reasons the linear model assumption may be unreasonable, and it is more meaningful to construct a better-integrated stock selection model based on different feature selection and nonlinear stock price trend prediction methods. In this paper, the features are selected by various feature selection algorithms, and the parameters of the machine learning-based stock price trend prediction models are set through time-sliding window cross-validation based on 8-year data of Chinese A-share market. Through the analysis of different integrated models, the model performs best when the random forest algorithm is used for both feature selection and stock price trend prediction. Based on the random forest algorithm, a long-short portfolio is constructed to validate the effectiveness of the best model.https://ieeexplore.ieee.org/document/8968561/Stocktrend predictionmachine learningfeature selectionlong-term investment |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Xianghui Yuan Jin Yuan Tianzhao Jiang Qurat Ul Ain |
| spellingShingle |
Xianghui Yuan Jin Yuan Tianzhao Jiang Qurat Ul Ain Integrated Long-Term Stock Selection Models Based on Feature Selection and Machine Learning Algorithms for China Stock Market IEEE Access Stock trend prediction machine learning feature selection long-term investment |
| author_facet |
Xianghui Yuan Jin Yuan Tianzhao Jiang Qurat Ul Ain |
| author_sort |
Xianghui Yuan |
| title |
Integrated Long-Term Stock Selection Models Based on Feature Selection and Machine Learning Algorithms for China Stock Market |
| title_short |
Integrated Long-Term Stock Selection Models Based on Feature Selection and Machine Learning Algorithms for China Stock Market |
| title_full |
Integrated Long-Term Stock Selection Models Based on Feature Selection and Machine Learning Algorithms for China Stock Market |
| title_fullStr |
Integrated Long-Term Stock Selection Models Based on Feature Selection and Machine Learning Algorithms for China Stock Market |
| title_full_unstemmed |
Integrated Long-Term Stock Selection Models Based on Feature Selection and Machine Learning Algorithms for China Stock Market |
| title_sort |
integrated long-term stock selection models based on feature selection and machine learning algorithms for china stock market |
| publisher |
IEEE |
| series |
IEEE Access |
| issn |
2169-3536 |
| publishDate |
2020-01-01 |
| description |
The classical linear multi-factor stock selection model is widely used for long-term stock price trend prediction. However, the stock market is chaotic, complex, and dynamic, for which reasons the linear model assumption may be unreasonable, and it is more meaningful to construct a better-integrated stock selection model based on different feature selection and nonlinear stock price trend prediction methods. In this paper, the features are selected by various feature selection algorithms, and the parameters of the machine learning-based stock price trend prediction models are set through time-sliding window cross-validation based on 8-year data of Chinese A-share market. Through the analysis of different integrated models, the model performs best when the random forest algorithm is used for both feature selection and stock price trend prediction. Based on the random forest algorithm, a long-short portfolio is constructed to validate the effectiveness of the best model. |
| topic |
Stock trend prediction machine learning feature selection long-term investment |
| url |
https://ieeexplore.ieee.org/document/8968561/ |
| work_keys_str_mv |
AT xianghuiyuan integratedlongtermstockselectionmodelsbasedonfeatureselectionandmachinelearningalgorithmsforchinastockmarket AT jinyuan integratedlongtermstockselectionmodelsbasedonfeatureselectionandmachinelearningalgorithmsforchinastockmarket AT tianzhaojiang integratedlongtermstockselectionmodelsbasedonfeatureselectionandmachinelearningalgorithmsforchinastockmarket AT quratulain integratedlongtermstockselectionmodelsbasedonfeatureselectionandmachinelearningalgorithmsforchinastockmarket |
| _version_ |
1724187425234747392 |