Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Computing | en_US |
| dc.creator | Tse, Ah-shan | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/1201 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | A trading system for stock selection using neural network | en_US |
| dcterms.abstract | This study aims to develop a computer system that employs neural network technology to produce advice to investors on what stocks to buy/sell and when these transactions should be carried out. Since the return rate of each stock (in terms of capital/ price increase) will fluctuate up or down relative to the market average, by investing in the rising stocks to replace those falling ones in a portfolio, the investor should be able to earn a profit which is above market average. The Dow Theory proposes that price fluctuations are results of three simultaneous movements: the primary trend lasting for months or years, the secondary trend lasting for weeks or months and the minor random moves lasting for hours or weeks. If trends do exist, we can establish reasonable guess for the near future based on the recent historical past. The historical trading data, i.e. price movements and volume of transactions, are transformed into technical indicators and fed into a neural network to produce the output which is the forecast of a short term return rate for a stock. Stocks are then ranked in accordance with their forecast return rate. Those on the top of the list should be "favour" in the market. A set of mechanical rules is developed to interpret the ranked list: if the ranking of a stock on hand stays in the top ten, hold it; if it falls below ten for a consecutive four weeks, replace it with one in the top ten not yet held. The trading system is developed with Shanghai stock market data during 20.12.93 - 25.12.95. A simulation is performed with data during 8.1.96 - 16.12.96 and the results show that an investor can achieve a return rate of 5.53 at the end of the trading period while the average return rate in the market is only 0.33. | en_US |
| dcterms.extent | viii, 98 leaves : ill. ; 30 cm | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 1998 | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.LCSH | Stock price forecasting -- Mathematical models | en_US |
| dcterms.LCSH | Investment analysis -- Data processing | en_US |
| dcterms.LCSH | Neural networks (Computer science) | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b14391053.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 3.68 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/200/1201