Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Computing | en_US |
| dc.creator | Lee, Man-shun | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/5855 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | DSS of portfolio optimization using genetic algorithm | en_US |
| dcterms.abstract | The dissertation presented the building of a DSS (Decision Support System) that used Genetic Algorithm in optimizing the selection of various assets in the Hong Kong stock market in order to achieve an optimized Portfolio. The problem was a typical Resource allocation problem to optimize the objective. It has been quite a few research works on applying Genetic Algorithm in Portfolio Optimization, there was study in exploring the use of tree structure in genomic representation, while the array representation has been blamed for held responsible for not effectively inherit parents traits in the cross-over (reproduction) stage. The genomic representation presented in this dissertation was still using array representation; moreover the suggested representation method offered the mechanism to pass the good combination assets into the next generation. Furthermore the Genetic Algorithm proposed in this Dissertation took into account of the fact that stock trading in the market has to be conducted in lots, there was no fractional lots can be purchased, while many researches commonly assumed the fractional lots transaction was possible if the capital amount was big enough such as corporate investor. The Genetic Algorithm representation in this dissertation did not make use of the normalization, which could lead to the problem of creating fractional lots in the solution space. Consequently the suggested representation made the problem becoming an integer programming problem as well. The initial experimental results showed a property of the Sharpe Ratio that the author not awarded before. It also shred a new light on the bottle neck of the optimization approach and DSS construction. The dissertation suggested a direction of further work on improving the processing speed of the DSS. It was believed the application of the proposed Array representation could apply. Genetic algorithm effectively and the construction of a DSS in helping home investor was possible. | en_US |
| dcterms.alternative | Decision support system of portfolio optimization using genetic algorithm | - |
| dcterms.extent | x, 54 leaves : ill. (some col.) ; 31 cm. | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2010 | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.LCSH | Stock exchanges -- China -- Hong Kong -- Data processing. | en_US |
| dcterms.LCSH | Decision support systems | en_US |
| dcterms.LCSH | Genetic algorithms | en_US |
| dcterms.LCSH | Portfolio management -- Mathematical models | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b23910896.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 3.15 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/200/5855