Spatio-Temporal Factors Affecting Short-Term Public Transit Passenger Demand Prediction: A Review

In public transit (PT) planning, passenger demand forecasting is an important process to periodically update operation management and planning infrastructure in the future. In the past, many researchers considered passenger demand forecasting a fundamental need for transportation planning and developed forecasting models based on statistical methods and Artificial Intelligence (AI). To increase the precision of the model, spatial and temporal attributes that influence the passenger movement at the station level, corridor level, and network level, are need to be considered. Hence, in this study, a detailed literature review is carried out to understand the pros and cons of various methods used in passenger demand forecasting and how distinctively spatial and temporal attributes are used in the development of the models. External factors like weather and events are also considered by the researchers in the development of the model. In the end, what are the challenges in the PT passenger demand forecasting are discussed and directions for future research are given.