Wavelet neural networks for stock trading and prediction
The main aim of this report is to study the topic of Wavelet Neural Networks, and see how they are useful for stock market non-linear time series prediction. To do this, the theories of wavelet analysis, neuron network, and the combination of WNN have been studied. Following that, some key considera...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/54400 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | The main aim of this report is to study the topic of Wavelet Neural Networks, and see how they are useful for stock market non-linear time series prediction. To do this, the theories of wavelet analysis, neuron network, and the combination of WNN have been studied. Following that, some key considerations in constructing the WNN found out during the project and literature reading are discussed. This provides sufficient background to implement a WNN model and conduct testing on S&P 500 index. The experiment result shows that thought the prediction ability of WNN is powerful, its performance is not stable. |
|---|