A mobile application system based on time series forecasting for selecting parking lots

Finding parking vacancies is a common problem in densely-populated areas. To support a driver's parking lot selection, besides the factors of price rate and distance to destination, vacancy number forecasting for neighboring parking lots of the destination, upon one's arrival time is essential. Therefore, the aim of this study is to develop a time series forecasting method for selecting parking lots, named ParkSelect, and to implement a mobile application system, named ParkForecast. All the experiments show that ParkSelect is effective.