“Managing Appointment-Based Services in the Presence of Walk-in Customers” by Dr. Nan Liu
Dr. Nan Liu
Department of Operations Management
Carroll School of Management, Boston College
Walk-in customers (or, “walk-ins” for short) are often welcome and accepted in the service industries. As walk-ins arrive spontaneously without advance notice, they may interrupt a service organization’s daily operations, in particular the service of those scheduled customers. To handle the tension between scheduled customers and walk-ins, we take a data analytics approach and develop the first optimization model to determine the optimal appointment schedule in the presence of potential walk-ins.
In this talk, I will first describe an exploratory empirical study, which shows that unscheduled walk-in process can be quite complex and may not follow a (nonhomogeneous) Poisson process as assumed by most prior literature. Then, I will introduce an elegant optimization model that can handle almost any general walk-in process as well as other possible uncertainties in the system, e.g., customer no-shows. Finally, I will present potential applications of this model and use data from practice to demonstrate a significant cost reduction (42%-73% on average) if providers were to switch from current practice (which tends to overlook walk-ins in planning) to our proposed schedules.
This is joint work with Shan Wang and Guohua Wan from Shanghai Jiao Tong University.