Stock trading using computational intelligence
Computational Intelligence has been widely used in recent years in many areas, such as speech recognition, image analysis, adaptive control and time series prediction. This research attempts to explore the usefulness of neural network and support vector machine in financial market. Two popular stock...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2010
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/40173 |
| _version_ | 1826118115588571136 |
|---|---|
| author | Zhu, Ming. |
| author2 | Wang Lipo |
| author_facet | Wang Lipo Zhu, Ming. |
| author_sort | Zhu, Ming. |
| collection | NTU |
| description | Computational Intelligence has been widely used in recent years in many areas, such as speech recognition, image analysis, adaptive control and time series prediction. This research attempts to explore the usefulness of neural network and support vector machine in financial market. Two popular stock market indexes have been studied: Hong Kong Hang Seng Stock Index and Dow Jones Transportation Index. The performance of neural network and support vector machine are evaluated in two dimensions: error in forecasting and trading profits.
Popular technical indicator, percentage price oscillator (PPO), has been selected as training input and output. Predictive models use previous 8 days PPO to forecast future 5 days PPO. Empirical results on Hong Kong Hang Seng Index show that multilayer perceptron optimized with GA (MLP-GA) trading system obtain 6.71 times of original capital from 1997-1-29 to 2007-3-8, totally 2500 trading days. While support vector regression optimized by genetic algorithms (SVR-GA) trading system generates 5.705 times of original capital during the same time horizon. In contrast, conventional non-predictive trading system only produces 2.064 times of starting equity. “Buy and Hold” strategy gives 1.605 times return to investors. A recent published fuzzy trading system provides 5.781 dollars as final equity for 1 dollar initial investment.
Further evaluations of two intelligent trading systems have been made. A back test using the same parameters and same assumptions on Dow Jones Transportation Index have further proved the robustness of the proposed trading systems. MLP-GA trading system provides 4.87 times of initial capital and SVR-GA trading system obtains 5.168 as final equity. These two intelligent trading systems again outperform conventional trading system, which generate 2.805 dollars for 1 dollar investment. |
| first_indexed | 2024-10-01T04:38:26Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/40173 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:38:26Z |
| publishDate | 2010 |
| record_format | dspace |
| spelling | ntu-10356/401732023-07-07T17:08:14Z Stock trading using computational intelligence Zhu, Ming. Wang Lipo School of Electrical and Electronic Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Computational Intelligence has been widely used in recent years in many areas, such as speech recognition, image analysis, adaptive control and time series prediction. This research attempts to explore the usefulness of neural network and support vector machine in financial market. Two popular stock market indexes have been studied: Hong Kong Hang Seng Stock Index and Dow Jones Transportation Index. The performance of neural network and support vector machine are evaluated in two dimensions: error in forecasting and trading profits. Popular technical indicator, percentage price oscillator (PPO), has been selected as training input and output. Predictive models use previous 8 days PPO to forecast future 5 days PPO. Empirical results on Hong Kong Hang Seng Index show that multilayer perceptron optimized with GA (MLP-GA) trading system obtain 6.71 times of original capital from 1997-1-29 to 2007-3-8, totally 2500 trading days. While support vector regression optimized by genetic algorithms (SVR-GA) trading system generates 5.705 times of original capital during the same time horizon. In contrast, conventional non-predictive trading system only produces 2.064 times of starting equity. “Buy and Hold” strategy gives 1.605 times return to investors. A recent published fuzzy trading system provides 5.781 dollars as final equity for 1 dollar initial investment. Further evaluations of two intelligent trading systems have been made. A back test using the same parameters and same assumptions on Dow Jones Transportation Index have further proved the robustness of the proposed trading systems. MLP-GA trading system provides 4.87 times of initial capital and SVR-GA trading system obtains 5.168 as final equity. These two intelligent trading systems again outperform conventional trading system, which generate 2.805 dollars for 1 dollar investment. Bachelor of Engineering 2010-06-11T03:50:37Z 2010-06-11T03:50:37Z 2010 2010 Final Year Project (FYP) http://hdl.handle.net/10356/40173 en Nanyang Technological University 60 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Zhu, Ming. Stock trading using computational intelligence |
| title | Stock trading using computational intelligence |
| title_full | Stock trading using computational intelligence |
| title_fullStr | Stock trading using computational intelligence |
| title_full_unstemmed | Stock trading using computational intelligence |
| title_short | Stock trading using computational intelligence |
| title_sort | stock trading using computational intelligence |
| topic | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence |
| url | http://hdl.handle.net/10356/40173 |
| work_keys_str_mv | AT zhuming stocktradingusingcomputationalintelligence |