A Stochastic Goal Program for Employee Scheduling

Abstract

Deterministic goal programs for employee scheduling decisions attempt to minimize expected operating costs by assigning the ideal number of employees to each feasible schedule. For each period in the planning horizon, managers must first determine the amount of labor that should be scheduled for duty. These requirements are often established with marginal analysis techniques, which use estimates for incremental labor costs and shortage expenses. spically, each period in the planning horizon is evaluated as an independent epoch. An implicit assumption is that individual employees can be assigned to schedules with as little as a single period of work. If this assumption violates local work rules, the labor requirements parameters for the deterministic goal program may be suboptimal.As we show in this research, this well-known limitation can lead to costly staffing and scheduling errors. We propose an employee scheduling model that overcomes this limitation by integrating the labor requirements and scheduling decisions. Instead of a single, externally determined staffhg goal for each period, the model uses a probability distribution for the quantity of labor required. The model is free to choose an appropriate staffing level for each period, eliminating the need for a separate goal-setting procedure. In most cases this results in better, less costly decisions. In addition, the proposed model easily accommodates both linear and nonlinear under-and overstaffing penalties. We use simple examples to demonstrate many of these advantages and to illustrate the key techniques necessary to implement our model. We also assess its performance in a study of more than 1,700 simulated stochastic employee scheduling problems.

Optimization of volunteer labor assignments

“…However, much services research has been published in the area of labor scheduling, which is an assignment of labor to time periods (Bechtold et al, 1991). Most of the labor scheduling research assumes a single task being scheduled (Easton and Rossin, 1996;Mason et al, 1998;Thompson, 1992). However, some labor scheduling research also includes determining labor task assignments (Loucks and Jacobs, 1991;Love and Hoey, 1990;Ritzman et al, 1976).…”

“…Minimizing the total labor hours scheduled is a common TLA objective function (e.g., Mabert and Showalter, 1990;Mason et al, 1998), although others objective functions exist (Bechtold et al, 1991). Objective functions that also represent costs minimization include: minimize the number of employees scheduled (Baker et al, 1979;Easton and Rossin, 1991;Hung, 1994), minimize labor costs (Easton and Rossin, 1996;Jaumard et al, 1998;Lauer et al, 1994), minimize over-staffing (Loucks and Jacobs, 1991;Love and Hoey, 1990), and maximizing the utilization of employed labor (Jacobs and Bechtold, 1993). These are all highly correlated with minimizing total number of labor hours.…”

“…The previous section introduced four goals, and thus we will use a goal programming methodology. Goal programming has been used in TLA contexts (e.g., Brusco and Johns, 1995;Easton and Rossin, 1996;Jaumard et al, 1998). For example, Loucks and Jacobs (1991) minimized: (a) excess labor assignments and (b) squared deviations from employee work time targets.…”

Optimizing Service Attributes: The Seller's Utility Problem*

“…Unfortunately, the key operating expenses for many businesses, including most services, rarely behave this way. For example, direct labor costs tend to vary nonlinearly and discontinuously with changes in service attributes such as speed of service or service complexity (Easton & Rossin, 1996), and are influenced by staffing and scheduling policies, the use of technology, and other process decisions.…”

Research opportunities in service process design

“…Several researchers have examined service capacity (labor) scheduling issues in general (Easton and Rossin, 1996;Goodale and Tunc, 1997). Specific examples include staff scheduling at L.L.…”