| Author: | Lam, Chun-fat |
| Title: | Forecasting the currency exchange rates by recurrent neural network |
| Degree: | M.Sc. |
| Year: | 1996 |
| Subject: | Foreign exchange -- Forecasting Neural networks (Computer science) Hong Kong Polytechnic University -- Dissertations |
| Department: | Multi-disciplinary Studies |
| Pages: | 86 leaves : ill. ; 30 cm |
| Language: | English |
| Abstract: | The objectives of my dissertation are to forecast four currency exchange rates by recurrent neural network. The four currencies are Japanese Yen, Deutsche Mark, Pound Sterling and Swiss Franc. The most powerful approach in forecasting the rates is to find a law underlying the given dynamic process. If we can get the law and understand the initial condition, we will be able to provide good predictions of the future behaviour. However, the rates are found to be chaotic and the dynamic process is incomplete. We cannot find a deterministic model to understand the time series. From my research, I note that classical statistical methods such as Box-Jenkins method have many limitation in understanding the pattern of currency exchange rates. The second powerful approach in forecasting the rates is to discover some strong empirical regularities in the observations of the past exchange rates. Unfortunately, some regularities such as periodicity are masked by noise. The error in the specification of the initial condition will also grow exponentially with time. The noise is so serious that even Box-Jenkins method cannot model the time series of exchange rates properly. Forecasting the exchange rates is a very challenging task. However, recurrent neural network is found to be a powerful tool to handle this task. Recurrent neural network can approximate or reconstruct any nonlinear function. Once a recurrent neural network is trained properly, it not only understands the time series but also generalizes what it learns to provide good estimation of exchange rates in the near future. Forecasting the exchange rates in short term basis is found to be possible. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b12306721.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 2.52 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/200/5169