An intelligent decision support system for facility location

This dissertation examines the design and implementation of an intelligent decision support system (IDSS) for assisting facilities planners in improving the quality of strategic decision-making in facility location. A survey of past location studies was conducted to identify the major considerations of location analysts and to develop a hierarchy of factors for locating a manufacturing facility in the USA. Location evaluation is accomplished via a location model which is formulated as a linear additive multiattribute utility model. The microcomputer-based IDSS integrates an object-oriented expert system with other modeling tools, such as a database management system and a C-based interactive graphical user interface. The system incorporates subjective evaluations from management with objective, factual location data to recommend the best location. The system also makes transparent the justification for its recommendations by providing appropriate textual and graphical explanation facilities. System evaluation was accomplished to test the IDSS's accuracy and utility. The results of the system evaluation suggest that the system performs accurately and satisfactorily according to the design specifications and objectives. Future work is anticipated to enable decision-making at the city and site levels. Advanced concepts, such as an object-oriented database management system and a geographic information system (GIS) can be incorporated to further enhance the system's usefulness and performance.