Addressing parking challenges in downtown Pittsburgh
Authors: Tayo Fabusuyi, Robert C. Hampshire
This paper discusses the development of ParkPGH, a novel smart parking application that provides real time and predictive information on garage parking availability in downtown Pittsburgh. The initiative is in response to the increased demand for parking spaces in downtown Pittsburgh and the desire to improve drivers’ parking experiences. The application includes a predictive model that uses as input historical parking, weather and event data to provide estimates of available parking spaces. We provide an example of the model implementation using data from the Theater Square garage where we utilize neural network-based predictors and multiple net searches to generate estimates of parking availability. Provision was also made for binary classifiers given the need to reduce the possibility of Type II errors. Outcome measures show that more than 50% of respondents reported a reduction in parking search time with the magnitude ranging from a minute to more than six minutes.