A knowledge based framework for selecting management science models

The authors present a knowledge-based framework for selecting management science models (solution methods) for a given problem. This framework considers the resources available to solve the problem and the context in which the problem is being solved as input parameters for model selection. Abstraction levels are presented for organizing management science models that facilitate the search process. `Frame´ is chosen as the preferred knowledge representation method. The proposed approach utilizes a number of special-purpose slots to facilitate knowledge representation and technique selection. Relevant issues for knowledge-base development are discussed. One of the major advantages of the proposed framework is that it analyzes relevant problem characteristics in the context of the information available for the problem and then tries to identify a solution model based on that information. This approach emphasizes that not only the problem description but also the resources available to solve the problem and the environment in which the problem is being solved are important for choosing an appropriate problem solver