Financial forecasting : a neural network approach
In recent years, neural networks have become increasingly popular in making stock market predictions. Much research on the applications of neural networks for solving business problems have proven their advantages over statistical and other methods. Advantages include fault and noise tolerance, robu...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/54016 |
| _version_ | 1826127129738215424 |
|---|---|
| author | Tay, Keane Ke Xun. |
| author2 | Chen Chun-Hsien |
| author_facet | Chen Chun-Hsien Tay, Keane Ke Xun. |
| author_sort | Tay, Keane Ke Xun. |
| collection | NTU |
| description | In recent years, neural networks have become increasingly popular in making stock market predictions. Much research on the applications of neural networks for solving business problems have proven their advantages over statistical and other methods. Advantages include fault and noise tolerance, robustness, and adaptability due to the interconnected processing elements that can be “trained” to learn new patterns. The neural network approach, essentially a data mining method, is well founded on the theory that the historic data holds the essential memory for predicting the future direction. This technology is designed to help investors discover hidden patterns from the historic data that have probable predictive capability in their investment decisions.
Today, the prediction of stock markets is regarded as a challenging task of financial time series prediction. Data analysis is one way of predicting the future movements of stock prices.
This study’s aim is to use artificial neural networks for the prediction of stock market prices. Experimental results show that the proposed forecasting model is an effective tool for forecasting stock prices. Furthermore, the neural network would be trained with different variations of the network architecture, finally presenting the optimal neural network architecture and the input combination that produces the best forecasting results. The neural network trading system has also proved to yield higher returns than several other investment strategies. |
| first_indexed | 2024-10-01T07:03:41Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/54016 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:03:41Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/540162023-03-04T19:23:56Z Financial forecasting : a neural network approach Tay, Keane Ke Xun. Chen Chun-Hsien School of Mechanical and Aerospace Engineering Khoo Li Peng DRNTU::Engineering::General In recent years, neural networks have become increasingly popular in making stock market predictions. Much research on the applications of neural networks for solving business problems have proven their advantages over statistical and other methods. Advantages include fault and noise tolerance, robustness, and adaptability due to the interconnected processing elements that can be “trained” to learn new patterns. The neural network approach, essentially a data mining method, is well founded on the theory that the historic data holds the essential memory for predicting the future direction. This technology is designed to help investors discover hidden patterns from the historic data that have probable predictive capability in their investment decisions. Today, the prediction of stock markets is regarded as a challenging task of financial time series prediction. Data analysis is one way of predicting the future movements of stock prices. This study’s aim is to use artificial neural networks for the prediction of stock market prices. Experimental results show that the proposed forecasting model is an effective tool for forecasting stock prices. Furthermore, the neural network would be trained with different variations of the network architecture, finally presenting the optimal neural network architecture and the input combination that produces the best forecasting results. The neural network trading system has also proved to yield higher returns than several other investment strategies. Bachelor of Engineering (Mechanical Engineering) 2013-06-11T07:50:52Z 2013-06-11T07:50:52Z 2013 2013 Final Year Project (FYP) http://hdl.handle.net/10356/54016 en Nanyang Technological University 58 p. application/pdf |
| spellingShingle | DRNTU::Engineering::General Tay, Keane Ke Xun. Financial forecasting : a neural network approach |
| title | Financial forecasting : a neural network approach |
| title_full | Financial forecasting : a neural network approach |
| title_fullStr | Financial forecasting : a neural network approach |
| title_full_unstemmed | Financial forecasting : a neural network approach |
| title_short | Financial forecasting : a neural network approach |
| title_sort | financial forecasting a neural network approach |
| topic | DRNTU::Engineering::General |
| url | http://hdl.handle.net/10356/54016 |
| work_keys_str_mv | AT taykeanekexun financialforecastinganeuralnetworkapproach |