Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Hospitality unit diagnosis: an expert system approach

Balfe, Andrew J. (1998) Hospitality unit diagnosis: an expert system approach. Master of Science thesis, Dublin City University.

Abstract
Formal methods of management problem-solving have been extensively researched. However, these concepts are incomplete in that they assume a problem has been correctly identified before initiating the problem-solving process. In reality management may not realise that a problem exists or may identify an incorrect problem. As a result, considerable time and effort may be wasted correcting symptoms rather than the true problem. This research describes the development of a computerised system to support problem identification. The system focuses specifically on the area of hospitality management, encompassing causes and symptoms of prominent problems in the hospitality industry. The system is based on knowledge rather than data. Research has shown that Expert Systems allow reasoning with knowledge. As a result, Expert Systems were selected as an appropriate technology for this application. Development is undertaken from the perspective of a hotel manager, using appropriate software development tools. The required knowledge is generally obtained from either expert interviews or textbook analysis. Gaining commitment from sufficient industry experts proved too difficult to allow the use of the former method, and therefore the latter method was utilised. However, knowledge acquired in this manner is limited in both quality and quantity. In addition, essential experience based judgmental knowledge is not available from this source. To counteract this, the personal knowledge of the author, a qualified hotel manager, was used. When developing an Expert System, knowledge acquisition and representation are of paramount importance. In this research, these issues are problematic due to the broad interdisciplinary nature and scope of hospitality management. To counteract this problem, some structure was required. Finance, Marketing, Personnel, Control, and Operations were selected as important functions within the hospitality business and therefore were represented within the system for diagnosis. A modular approach was used with modules being developed for each functional area. An initial top level module performs a general diagnosis, and then separate subordinate modules diagnose the functional areas. This research established that the knowledge required for incorporation into such a system is not available. The possibility of acquiring this knowledge is beyond the bounds of this research. However, sufficient marketing knowledge was sourced to facilitate the development of the Expert System structure. This structure demonstrates the application of the technology to the task and could subsequently be used when more knowledge is elicited. The research findings show that the development of a modular diagnostic system is possible using an Expert System Shell. The major limiting factor encountered is the total lack of the relevant knowledge. As a result, further research is recommended to establish the factors influencing diagnosis in the hospitality industry.
Metadata
Item Type:Thesis (Master of Science)
Date of Award:1998
Refereed:No
Supervisor(s):Mac Donaill, Ciaran and O’Connor, Peter
Uncontrolled Keywords:Management science; Data processing; Hospitality industry
Subjects:Computer Science > Software engineering
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 3.0 License. View License
ID Code:18322
Deposited On:11 Jun 2013 14:51 by Celine Campbell . Last Modified 05 Aug 2021 12:06
Documents

Full text available as:

[thumbnail of Andrew_J_Balfe_20130307162924.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
2MB
[thumbnail of Andrew_J_BalfeV1_20130307163214.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
4MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record