| Author: | Wong, Shing-yue Samuel |
| Title: | Stock portoflio [i.e. portfolio] optimization using genetic algorithm |
| Other Title: | Stock portfolio optimization using genetic algorithm |
| Degree: | M.Sc. |
| Year: | 2002 |
| Subject: | Hong Kong Polytechnic University -- Dissertations Stock price forecasting -- Mathematical models Genetic algorithms |
| Department: | Department of Computing |
| Pages: | [165] leaves : ill. ; 30 cm. |
| Language: | English |
| Abstract: | Lots of literature on stock portfolio optimization by using artificial intelligence has been written. Most of them are based on time series tracking and factors model. The use of artificial intelligence on mean variance theorem is seldom encountered. Given the simple and elegant mean variance theorem, stock portfolio optimization can be approached in a new perspective by using expected return of stock over a period and its corresponding standard deviation as a yardstick for the measurement of stock portfolio performance. The purpose of the study is to search for the optimal combination of weights in a selected basket of stock to maximize its performance. By using the yardsticks of mean variance theory as a yardstick of measurement, the portfolio performance is compared against the performance of Hang Seng index. After due consideration on the alternatives on artificial intelligence tools, neural network, expert systems, fuzzy systems and genetic algorithm, the application of genetic algorithm for this type of parallel search process is considered suitable. The Matlab Genetic Algorithm Optimization Toolbox (GAOT) is used to conduct the analysis. The study is divided into two parts. The first part is to use genetic algorithm base on the pass data to find the optimal stock portfolio that outperforms Hang Seng index in terms of higher rate of return with lower risk. The result is positive. The second part makes use of the selected weight of the optimal portfolio in the result of part one to make projections on future return in the next investment period. The result reveals a positive projected return that is highly correlated to the pass return where it is based. But the projected return is lower than the pass return and only projected return on longer periods (over 5 days) outperforms Hang Seng Index. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b17523497.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 8.29 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/200/5587