Article ID: | iaor2006865 |
Country: | Netherlands |
Volume: | 41 |
Issue: | 1 |
Start Page Number: | 84 |
End Page Number: | 111 |
Publication Date: | Nov 2005 |
Journal: | Decision Support Systems |
Authors: | French S., Papamichail K.N. |
Keywords: | decision: studies, artificial intelligence: decision support |
Intelligent Decision Support Systems (DSSs) use expert systems technology to enhance the capabilities of decision makers (DMs) in understanding a decision problem and selecting a sound alternative. Because of the people-centred focus of such technologies, it is important not only to assess their technical aspects and overall performance but also to seek the views of potential users. This paper draws from the literature to classify methods for assessing intelligent Decision Support Systems and discusses our experiences in developing, operating and evaluating an intelligent decision support system for nuclear emergencies. The system assists decision makers in the formulation and ranking of alternatives and communicates its recommendation in a natural language form. The application highlights insights from the development process and shortcomings of existing assessment methods. Lessons learned from the study, challenges encountered and recommendations for future practices are discussed.