Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Computing | en_US |
| dc.contributor.advisor | You, Jane (COMP) | en_US |
| dc.creator | Wu, Wenjun | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/14136 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | en_US |
| dc.rights | All rights reserved | en_US |
| dc.title | Machine learning approaches to picking A-shares stocks : a comparative analysis | en_US |
| dcterms.abstract | With an emphasis on the Chinese stock market, this study investigates the integration of advanced machine learning (ML) techniques and large language models (LLMs) in financial modeling. It introduces an innovative approach to stock market prediction by developing the ChatGPT Score, an LLMs-driven sentiment analysis factor. The research compares the traditional Fama-French five-factor (FF5) model with its augmented version, FF5+ChatGPT Score, and evaluates linear regression models against various ML models, including Random Forests, Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Category Boosting (CatBoost), within the context of both five- and six-factor frameworks. | en_US |
| dcterms.abstract | Empirical investigation demonstrates that the ChatGPT Score outperforms traditional sentiment technologies such as SnowNLP. Besides, the inclusion of the ChatGPT Score in the FF5 model significantly improves its predictive capacity. The study highlights that ML models, CatBoost and Random Forests, are very efficient for managing portfolios. It also emphasizes that LLMs-driven sentiment analysis can improve the financial models' performance. | en_US |
| dcterms.abstract | This research utilizes Sample Bootstrapping (SB) for statistical validation. A retrospective study validates the models' practical effectiveness. Furthermore, feedback from professionals in the business confirms the practical significance of integrating these approaches into investment plans. While the results are promising, the study acknowledges the limitations of current models. For the future research directions, it proposes implementing deep learning techniques based on neural networks. | en_US |
| dcterms.abstract | In brief, this research emphasizes the advantages of combining traditional financial models with advanced ML and LLMs-driven sentiment analysis. This suggests a shift towards more advanced techniques for analyzing financial markets. | en_US |
| dcterms.extent | 128 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2025 | en_US |
| dcterms.educationalLevel | Eng.D. | en_US |
| dcterms.educationalLevel | All Doctorate | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 8588.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 5.38 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/14136