Strategic planning for investment in R&D using decision analysis and mathematical programming

This paper investigates the strategic planning and investments associated with research and development (R&D) project selection and budgeting within a division of an aerospace firm. A model is described that is used in an R&D planning environment where considerable risks result from technological, economic, governmental, and market factors. Several forms of a multi-attribute utility (MAU) objective function are maximized using mathematical programming techniques. Approximate methods, including compromise programming and goal programming, are evaluated and yield results that are reasonably dose to and require less computation than more exact methods. Solutions are used to recommend to management an R&D portfolio that maximizes expected utility for the division.