An effective supervisory function must allocate workload efficiently and optimize limited work hours with respect to a variety of operational requirements. These requirements often vary and entails a fast and dynamic model to be considered effective. Work allocation has typically been accomplished either through manual planning with considerations or constraints of very limited complexity, or by deterministic methods; requiring inordinate amounts of work hours which are typically incapable of adapting to changes in the environment. The methods and models presented here utilize forecasting techniques, analytic hierarchy process, and genetic algorithm (as search heuristic) to find a good sufficient allocation solution that can be performed quickly in rapidly changing process environment. Improvements introduced in this paper is projected to save 84 hours’ worth of work per month.An effective supervisory function must allocate workload efficiently and optimize limited work hours with respect to a variety of operational requirements. These requirements often vary and entails a fast and dynamic model to be considered effective. Work allocation has typically been accomplished either through manual planning with considerations or constraints of very limited complexity, or by deterministic methods; requiring inordinate amounts of work hours which are typically incapable of adapting to changes in the environment. The methods and models presented here utilize forecasting techniques, analytic hierarchy process, and genetic algorithm (as search heuristic) to find a good sufficient allocation solution that can be performed quickly in rapidly changing process environment. Improvements introduced in this paper is projected to save 84 hours’ worth of work per month.