| Author: | Lee, Kai-leung |
| Title: | Optimization of trading strategy by genetic algorithms and wavelet transform with an Internet application to the Hong Kong stock option |
| Degree: | M.Sc. |
| Year: | 1999 |
| Subject: | Stock options -- China -- Hong Kong -- Decision making -- Data processing Investments -- China -- Hong Kong -- Decision making -- Data processing Time-series analysis -- Data processing Internet Expert systems (Computer science) Genetic algorithms Wavelets (Mathematics) Hong Kong Polytechnic University -- Dissertations |
| Department: | Multi-disciplinary Studies Department of Computing |
| Pages: | v, 106 leaves : ill. ; 31 cm |
| Language: | English |
| Abstract: | Financial information such as news, quotations of financial instruments, and economic data, etc., is critical to making investment decisions. However, access to these information may require additional system facilities and membership rights. Yet, a trader may need to extract only those useful information for analysis before arriving at a desired trading strategy. One important class of financial information is financial time series. Financial time series often exhibits irregularity or spikes. Also, it is time-varying and non-linear in the distribution of price variation. Analysis usually applies to multiple financial series. With such model complexities and the cumbersome of information extraction of large amount of data periodically, the aim of this dissertation attempts to develop an Internet application to assist general traders for making investment decisions by optimizing trading strategy in terms of profit based on the data collected and extracted from the Internet. The problem domain is the Hong Kong Stock Option. Genetic Algorithms are computer simulated optimization search methodology inspired by natural evolutionary process and environmental survival. It is used to optimize the search for optimal strategy for stock option trading. Developing trading strategy requires modeling of the market conditions. The behavior of financial time series provides this information. Financial time series often exhibits outliers like short transients or spikes. Wavelet transform is useful in its ability to localize data in time-series and capture short lived transients to give better model accuracy. This dissertation aims at developing a stock option trading expert system to provide optimal trading strategies by applying genetic algorithms to explore optimality over a set of option trading rules and wavelet transform to capture high frequencies behavior in financial time series. The resulted trading strategy is searched with the goal of maximizing profit and minimizing risk. Hong Kong stock option and stock daily closing traded records are available in the Internet. This availability makes adaptive optimization possible for the changing market. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b14719356.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 3.31 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/200/317