| Author: | Li, Wen |
| Title: | Factor based asset allocation with machine learning in China |
| Advisors: | Chen, Te-feng (AF) |
| Degree: | DFinTech |
| Year: | 2025 |
| Department: | Faculty of Business |
| Pages: | 1 volume (various pagings) : color illustrations |
| Language: | English |
| Abstract: | This thesis focuses on the application and optimization of factor based asset allocation in China, aiming to build a scientific and effective framework. With the needs of financial asset allocation increase from Chinese investors, exploration of the theory and practice of asset allocation will help to further enrich and improve China's investment theory system and provide more theoretical basis for investment decision making. Through analysis of characteristics and practice, factor based asset allocation is applying to Chinese market with optimization with machine learning technology. At deterministic factors, which improves the factor selection framework, as well as build a bridge of machine learning and asset allocation from factor angle. At the level of application practice, the factor mimicking portfolio is applied to the Chinese market, which realizes the tradability of factors and solves the problem of low frequency of macroeconomic data update, and the optimized factor based allocation framework has been validated by latest Chinese market data. The empirical results demonstrate that the factor based asset allocation strategy is significantly well performed than the traditional allocation strategies regarding risk adjusted return. The study also found that machine learning models excel at predicting factor mimicking portfolio returns, effectively improving portfolio returns and stability. Finally, the paper proposes future research directions, including extended factor mining and further exploration of the use of machine learning algorithms in asset allocation. This paper systematically applies machine learning technology to factor investment strategies in China market for first time, offering a fresh viewpoint and tools for research in this field. Through comprehensive data analysis and empirical experiment, the effectiveness of factor investment in Chinese financial market is strongly confirmed, and a comprehensive asset allocation method that considers income acquisition and risk control is proposed, aiming to provide Chinese investors with a scientific and effective asset allocation path and lay a foundation for deepening relevant academic research. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 8534.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 5.12 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/200/14071