Article ID: | iaor1996966 |
Country: | Netherlands |
Volume: | 61 |
Issue: | 1/2 |
Start Page Number: | 114 |
End Page Number: | 121 |
Publication Date: | Aug 1992 |
Journal: | European Journal of Operational Research |
Authors: | Edwards John S. |
Keywords: | artificial intelligence: expert systems |
Historically, the fields of Decision Support Systems and Expert Systems grew up from different backgrounds; Management Informtion Systems and Artificial Intelligence, respectively. As a result, many people still regard them as unrelated fields, although Operational Researchers are working in both of them. Expert Systems in particular have found it difficult to escape from an image of being isolated; not just from Decision Support Systems, but from all other types of computer system. Successful applications appeared to be confined to very well-defined tasks; either small systems for tasks of an operational nature, or large systems requiring expensive specialised computer support. The spread of Expert Systems into management and administrative applications from the scientific/technical domains of the early systems has been very slow. The view put forward in this paper is that for Expert Systems to be applied to problems in management or administration, the traditional ‘closed-world’ picture of an Expert System is usually inadequate. The real manifestation of the Expert System’s role (and indeed that of the human expert) involes much more negotiation and interaction than in scientific/technical domains. The consequences for the resulting system are that it looks much more like the traditional picture of a Decision Support System than a classic standalone Expert System. The argument will be illustrated by reference to examples of ‘Expert System’ developments, including systems for production control, crime pattern analysis, telephone marketing, and the drawing up of contracts.