Research on Stock Price Prediction Model Based on Weighted Sufficient Dimension Reduction and Bagging Framework
DOI: 10.23977/infse.2024.050203 | Downloads: 4 | Views: 132
Author(s)
Yi Shen 1, Chi Qin 2
Affiliation(s)
1 China University of Petroleum (Beijing), Beijing, 100000, China
2 Guangxi University of Finance, Nanning, 530007, China
Corresponding Author
Yi ShenABSTRACT
Research on stock price prediction models based on multi-factor models has always been one of the hot directions in quantitative finance. The key lies in accurately mining factors that significantly impact stock prices and constructing prediction models that are both precise and robust. In light of this, we propose a stock price prediction method based on sufficient dimension reduction and the idea of model averaging. On the one hand, this method utilizes a weighted version of sliced inverse regression and mean-variance estimation as tools for factor mining. While reducing the curse of dimensionality, it can theoretically retain all the effective information of the original factors on stock prices completely. On the other hand, this method introduces the bagging model, which can effectively balance the variance and bias in the prediction model, thereby significantly enhancing the model's generalization ability. The results of actual data analysis show that compared to other methods, the proposed method has a smaller mean squared error and absolute error, and it possesses a certain degree of robustness. Moreover, when the sub-models use interpretable machine learning algorithms, the proposed method can not only perform accurate stock price predictions but also reveal the feature importance of each quantitative factor in stock price prediction.
KEYWORDS
Stock Price Prediction, Model Averaging, Factor MiningCITE THIS PAPER
Yi Shen, Chi Qin, Research on Stock Price Prediction Model Based on Weighted Sufficient Dimension Reduction and Bagging Framework. Information Systems and Economics (2024) Vol. 5: 19-25. DOI: http://dx.doi.org/10.23977/infse.2024.050203.
REFERENCES
[1] Liu Xiao. Research on Multi Factor Stock Forecasting Based on Quantitative Trading -Take the Shanghai and Shenzhen 300 Index an Example [D]. Soochow University, 2022.
[2] Wu Jiawei. Research on composite multi-factor quantitative stock selection scheme combining fundamental and technical factors [D]. Shanghai Normal University, 2022.
[3] Wang Xianhe. Research on a Dynamic Multi Factor Stock Selection Model Based on Recurrent Neural Network [D]. Northeast University of Finance and Economics, 2022.
[4] Banglong L, Jie L, Guanghui Y. Research on Stock Price Prediction Model based on GA Optimized SVM Parameters [J]. International Journal of Security & Its Applications, 2016, 10(7):269-280. DOI: 10. 14257/ijsia. 2016. 10.7.24.
[5] Du X, Chen K, Zhang T, et al. Multistep-Ahead Stock Price Forecasting Based on Secondary Decomposition Technique and Extreme Learning Machine Optimized by the Differential Evolution Algorithm [J]. Mathematical Problems in Engineering, 2020. DOI:10.1155/2020/2604915.
Downloads: | 7340 |
---|---|
Visits: | 146105 |
Sponsors, Associates, and Links
-
Accounting, Auditing and Finance
-
Industrial Engineering and Innovation Management
-
Tourism Management and Technology Economy
-
Journal of Computational and Financial Econometrics
-
Financial Engineering and Risk Management
-
Accounting and Corporate Management
-
Social Security and Administration Management
-
Population, Resources & Environmental Economics
-
Statistics & Quantitative Economics
-
Agricultural & Forestry Economics and Management
-
Social Medicine and Health Management
-
Land Resource Management
-
Information, Library and Archival Science
-
Journal of Human Resource Development
-
Manufacturing and Service Operations Management
-
Operational Research and Cybernetics