Providing Useful Information for Passengers Based on TTF Model

Taxis are an important part of public transportation in nowadays. Taking a vacant taxi has become a difficult problem due to the imbalance between demand and supply of taxi service. People want to know where is better to wait for a vacant taxi in order to save their time in the fast-paced city life. Helpful information could be provided to the passengers by mining the historical GPS traces generated by taxis. In this paper, we propose a model based on taxi traffic flow (TTF) model to measure the difficulty of taking a vacant taxi on the road segments nearby. Furthermore, we calculate probability and expected waiting time of taking a vacant taxi based on TTF model. Afterwards, we detect the hotspots on the road segments expecting to offer more available information. Our research is based on the real historical taxi GPS data generated by 12000 taxis in Beijing. We conduct experiments to validate our model eventually and the experimental results are in line with the actual situation well relatively.