Development of an expert system prototype for selecting demand forecasting methodologies

Pao Yue-kong Library Electronic Theses Database

Development of an expert system prototype for selecting demand forecasting methodologies

 

Author: Lee, Chi-wah
Title: Development of an expert system prototype for selecting demand forecasting methodologies
Degree: M.Sc.
Year: 1995
Subject: Business forecasting
Expert systems (Computer science)
Hong Kong Polytechnic University -- Dissertations
Department: Dept. of Computing
Pages: viii, 68, [13] leaves : ill. ; 30 cm
Language: English
InnoPac Record: http://library.polyu.edu.hk/record=b1205692
URI: http://theses.lib.polyu.edu.hk/handle/200/4340
Abstract: Forecasting is the art and science of predicting future events. Demand forecasting is the most basic activity in operations management of an organisation. It guides the company's scheduling and production control activities. Reliable forecasts enable managers to formulate production, capacity, and scheduling plans and systems, and serves as inputs to financial, marketing, and personnel planning. However, forecasting methods differ considerably with regard to factors such as cost, ease of use and potential accuracy. Choosing and applying an appropriate technique for a particular problem is not a trivial task; it is a complex, fuzzy process of making trade-offs. The choice of technique requires the forecaster to be knowledgeable and with experience, and the task is fundamental important as it has directly impact on the benefits, costs and hence ultimate satisfaction associated with forecasting. In existing practices, it is difficult to consider all relevant factors when selecting a forecasting method, and to have a mechanism for rapidly screening alternative methods. Thus there is difficulty to maintain flexibility in approaching new forecasting situations. It is believed that expert systems would offer great opportunities in tackling these problems. If knowledge and expertise for forecasting methods selection can be captured and made use of at any time and applied in general and not restricted to those specially trained, then there would be significant improvement in the quality of forecasting work in terms of accuracy and effectiveness, especially for those companies with limited expertise and resources in this area, such as smaller companies. A prototype which could deal with forecasting methods selection was developed to test the above hypothesis. Selection criteria were formulated and built into the knowledge base of the system using expert system shell, Guru, for matching forecasting situation characteristics with capabilities of different forecasting methods. The whole selection process involves an inferring phase and a ranking phase. A user evaluation was carried out and was mainly on two areas : the performance of the system, and the concept of applying expert systems in the forecasting methods selection decisions. On the whole, the research objectives have been quite successfully fulfilled when evaluating the performance of the prototype. And the valuers were of high acceptance of applying expert systems in forecasting methods selection application. Feedback from valuers in functional performance and usability of the prototype are valuable when developing the full working system.

Files in this item

Files Size Format
b12056923.pdf 2.628Mb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. 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.
  3. 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.

     

Quick Search

Browse

More Information