A Demand-Supply Oriented Taxi Recommendation System for Vehicular Social Networks

To realize the construction of intelligent transportation system, data mining based on large-scale taxi traces has become a hot research topic. A crucial direction for analyzing taxi GPS data set is to recommend cruising areas for taxi drivers. Most of the existing researches merely concentrate on how to maximize drivers' profits while overlooking the benefit of passengers. Such imbalance makes the existing solutions do not work well in a real-world environment. In this paper, we construct a recommendation system by jointly considering the profits of both drivers and passengers. Specifically, we first investigate the real-time demand-supply level for taxis and then make an adaptive tradeoff between the utilities of drivers and passengers for different hotspots. At last, the qualified candidates are recommended to drivers based on the analysis results. Simulation results indicate that the constructed recommendation system can achieve a remarkable improvement on the global utility and make equilibrium between the utilities of drivers and passengers, simultaneously.