Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Multi-disciplinary Studies | en_US |
| dc.contributor | Department of Computing | en_US |
| dc.creator | Wong, Wilson | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/2613 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | The fuzzy expert system for personal investment strategy | en_US |
| dcterms.abstract | Interest in investment has been increasing dramatically. A wide variety of investment tools are available. There is a large number of people who would like to invest. Nevertheless, professional investment advice can only be obtained from trained personnel or professional who gives advice based on his experience or the company policy. This expertise information is usually vague and fuzzy in nature, and hence difficult to be understood by the untrained investors. Thus, it is surely beneficial to develop a system that captures this domain knowledge and provides the investor with a professionally balanced investment strategy. Within this dissertation, three contributions are made. Firstly, investment knowledge is captured into a fuzzy expert system, which determines the investor's investment goals and a professionally balanced mixture of investment products that best meet all the investor's requirements. Secondly, it provides the investor an explanation for the suggested strategy. This lets the investor understand his own profile, the features, benefits, risks and potential returns of the investment prior to making a purchase. For novice investor, this serves as a good reference. Thirdly, this system helps banks or investment companies to keep the domain knowledge that would be lost due to resignation of domain expert. Also, it is a good guideline for the inexperienced staff. Approaches like neural network and expert system have been widely used in implementing financial planning systems. The domain knowledge of investment strategy is usually vague and fuzzy in nature. These strategists use some sort of heuristic approach and human capability of dealing with fuzzy and vague information to come up a strategy. However, traditional expert system cannot take in account such imprecise and incomplete information which, on the contrary, can be handled by fuzzy logic. For those using neural network, neural network has the learning capability but it lacks the explanation capability which can be solved by fuzzy ruled-based system. In contrast to the black box type NN containing numeric data, the fuzzy rules are very transparent as rules are explicitly stated. Intrinsically vague knowledge is typical of the decision processes involved in personal investment strategy. Linguistic descriptions of the investor's profile and investment strategy do not, by definition, represent a precise numeric concept and cannot be modelled in terms of crisp sets. For example, investor's profile may be described as 'high' risk tolerance while investment strategy, represented in terms of investment products weighting, may be expressed as 'very large' or 'small' portion of the investment amount in stocks. Fuzzy set theory and fuzzy logic provide an appropriate framework for the representation of these imprecise concepts and modes of reasoning. An investment expert system with a fuzzy inference model, for the construction of investment strategy is presented. Investment knowledge is represented in the form of relationships between combinations of investor profile and investment strategy / portfolio. The investor profile is then used by the knowledge base to infer the appropriate investment strategy / portfolio. Investment strategy / portfolio suggested by system is a function of many factors, including tolerance for risk, financial goals etc. It offers general advice and makes no specific recommendations. For example, it may recommend a portfolio which suggests investment in blue chip growth securities but doesn't specifically suggest which one. | en_US |
| dcterms.extent | ix, 80, [33] leaves : ill. ; 30 cm | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 1999 | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.LCSH | Fuzzy systems | en_US |
| dcterms.LCSH | Fuzzy logic | en_US |
| dcterms.LCSH | Expert systems (Computer science) | en_US |
| dcterms.LCSH | Finance, Personal | en_US |
| dcterms.LCSH | Investments | 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 | |
|---|---|---|---|---|
| b14605193.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 3.16 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/200/2613