Context-adaptive Graph Bike Flow Prediction Network for Public Transportation Infrastructure

The bike-sharing system is a crucial part of the new public transportation infrastructure. Stable management and dispatching measures are conducive to the orderly operation of urban public transportation infrastructure. The fundamental issue of managing bike-sharing systems is bike flow prediction. We published experimental data and results. We collect the trip data of Citi-Bike system in NYC, from 2019/1/1 to 2019/12/31. The data include: origin stations, destination stations (station ID, latitude and longitude), start time, and stop time.