| Author: | Kwong, Ng-fung |
| Title: | The fuzzy time series prediction system using chaos theory and fractal dimension |
| Degree: | M.Sc. |
| Year: | 2007 |
| Subject: | Hong Kong Polytechnic University -- Dissertations. Finance -- Mathematical models. Stock price forecasting. Time-series analysis. Prediction theory. |
| Department: | Department of Computing |
| Pages: | x, 87 leaves : ill. ; 30 cm. |
| Language: | English |
| Abstract: | In finance we are often left guessing at what series of events could have led to that bubble or crash. The economies behavior of stock prices, including apparent anomalies like market crashes, emerges as the result of a lot of complicated interactions. Interactions between companies, financial agents, governments and just chance. Emergence and complexity are words, often used synonymously, that describe a new concept of complex systems whose behavior cannot be understood in a simple manner. 'Complex systems' are systems with many interacting parts, in which simple rules (which specify how the system evolves) lead to complicated and unpredictable behavior. Thus complexity, like chaos theory and fractal dimension, it essentially describes the variation with a structure formed by a complex system or the degree to which such variation is present. Complexity is a more interesting kind of variation and one that is difficult to quantify. In addition, contemporary research takes the view financial time series prediction problems are highly complex and even chaotic and cannot be successfully modelled using classical non-linear models. However, there is an estimation of fractal dimension and numerical algorithm of chaos theory which are not completely accurate. For this reason, the new method of fuzzy estimation with fractal dimension that incorporates multi vector autoregressive process with chaotic signal has been proposed to solve the non-liner time series prediction problem. Chaos theory and fractal dimension are great achievement in the understanding of the mathematical principle at work in our universe. It shows us how under certain conditions, the complex system can behave predictably. The new approach was applied to the problem of Hong Kong Heng Sang Index (HSI) prediction involving the opening, closing, intraday-high, intraday-low prices and turnover. The experiment showed that the new approach is more accurate than the other contemporary non-linear time series models such as MLP, RBF, SVM and VAR. The solution is to implement fuzzy estimation with fractal dimension based on the paradigm of deterministic chaos and time series analysis to solve the nonlinear stock prediction problem. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b21668498.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/200/2008