|Title:||Applying a genetic fuzzy approach for stock price prediction|
|Subject:||Stock price forecasting -- China -- Hong Kong|
Hong Kong Polytechnic University -- Dissertations
Department of Computing
|Pages:||ii, 86 leaves : ill. ; 30 cm|
|Abstract:||With a proper set of fuzzy rules, fuzzy systems have been applied to different areas like industrial processes and financial tradings. The major issue in applying fuzzy systems is the acquisition of the rules. Expert knowledge and experience are usually required to define the fuzzy rules. In this study, we explore a new approach to extract the fuzzy rules from the data using Genetic Algorithms. Genetic Algorithms are search procedures inspired by the biological process of survival of the fittest. It is most useful in searching the optimal solution in a large solution space. Because Genetic Algorithms only need an evaluation function to operate, they are easy to hybridize with other techniques. As an application, we build a hybrid genetic fuzzy model to explore the Hong Kong stock market's behavior and to make predictions on the stock price/index. In the hybrid model, the genetic algorithm searches for the fuzzy rules that best matches the relationships between the macroeconomic data and the stock price/index. The fuzzy rules obtained can be used to analyze the patterns of the stock market. We compared this approach with the widely used linear regression model and found that the two approaches have similar performance in fitting with the past data. The hybrid genetic fuzzy model performs better at giving forecasts close to the actual values.|
Files in This Item:
|b1425881x.pdf||For PolyU Staff & Students||2.61 MB||Adobe PDF||View/Open|
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: