Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Electronic and Information Engineering | en_US |
| dc.contributor.advisor | Chi, Zheru George (EIE) | en_US |
| dc.creator | Zhou, Wenming | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/11186 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | en_US |
| dc.rights | All rights reserved | en_US |
| dc.title | Optimization of investment strategies using evolutionary computation | en_US |
| dcterms.abstract | The aim of this dissertation is to provide a method for developing optimized investment strategies using genetic programming. Previous work show that additional economic fundamentals data put into the model used for developing investment strategies can lead to improved results. For most prediction models based on AI or machine learning technology, too much input data may lead to dimension disaster. Genetic programming (GP) is a kind of evolution computation technology which can find optimized investment strategies by searching for combinations of economic factors. Previous studies have shown that it becomes extremely inefficient in computing when the number of factors increase. GP is seldom used in existing applications to develop optimized investment strategies based on massive indicators of economic fundamentals. In order to make use of the evolutionary algorithm to obtain better investment strategy, this dissertation proposed the idea of using nonlinear kernel function to greatly reduce the number of factors. We introduced the clustering algorithm and principal component analysis both are based on kernel function. Genetic programming algorithm are adopted to work on a small number of variables to search for strategies. In order to verify the effectiveness of our method, rule model of investment strategy is defined, and experiments are conducted using the genetic programming. The rule to maximize the revenue by buying and selling index funds was developed. Our experiments demonstrate that the nonlinear dimensionality reduction method based on Gaussian kernel function can effectively reduce the number of economic indicators, thus breaking the limit that GP algorithm can only work effectively on combining a small number of factors. The strategy found by GP algorithm run well on test data by gaining a compound annualized rate of 6.5% in mainland stock market of china, which can provide a useful reference for development of investment strategies. | en_US |
| dcterms.extent | x, 54 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2021 | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.LCSH | Investments -- Mathematics | en_US |
| dcterms.LCSH | Investment analysis -- Mathematics | en_US |
| dcterms.LCSH | Genetic programming (Computer science) | en_US |
| dcterms.LCSH | Genetic algorithms | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 5663.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 1.91 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/200/11186