MODEL SELECTION AND SEQUENCING IN DECISION SUPPORT SYSTEMS

A crucial problem confronting users of decision support systems (DSS) is the identification of an appropriate model or a sequence of models that may be used to solve a particular problem. This paper develops a procedure for model sequencing that permits the construction of ad hoc model chains. The proposed solution procedure limits the user's interaction with the DSS to conceptualizing the problem in terms of input/output requirements and overall problem objectives. A core of meta-knowledge is constructed around the model base which effectively shields users from the technical aspects of model implementation. If a single model in the model base cannot satisfy user requirements, the solution procedure seeks to obtain a string of models such that some performance measure (model processing cost or time) is minimized. A prototype system incorporating the model selection and integration methodology is described.