A Data-Driven Model of an Appointment-Generated Arrival Process at an Outpatient Clinic

In order to develop appropriate queueing models that can be applied to efficiently provide good service in a service system with arrivals by appointment, we carefully consider what stochastic arrival process models may be appropriate. We provide a guideline or template for creating stochastic arrival process models by carefully examining appointment and arrival data from an endocrinology clinic. In addition to three recognized sources of variability, (i) no-shows, (ii) extra unscheduled arrivals and (iii) deviations in the actual arrival times from the scheduled times, we find that the primary source of variability is variability in the daily schedule itself. We create detailed stochastic models that can be used to simulate the arrival process and analyze system performance. We develop a classification scheme that can be used to compare appointment systems and their performance.