One of the challenges of organizations providing services to the public is the effective resource allocation. Many service providers such as hospitals, city halls or department of motor vehicles suffer from a service demand, which is unevenly distributed over the day. In this work, we evaluate techniques for predicting the service demand. We use the wait time dataset collected from the websites of California Department of Motor Vehicles (DMV). We extract patterns of the service demand in form of wait time during each hour of a day and each day of a week. This information is used to train multiple machine learning models in order to predict the future wait time at DMV offices.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2013) studied this question.
Synapse has enriched one closely related paper. Consider it for comparative context: