Taxi service strategies, as the crowd intelligence ofmassive taxi drivers, are hidden in their historical time-stampedGPS traces. Mining GPS traces to understand the service strate-gies of skilled taxi drivers can benefit the drivers themselves, pas-sengers, and city planners in a number of ways. This paper intendsto uncover theefficientandinefficienttaxi service strategies basedon a large-scale GPS historical database of approximately 7600taxis over one year in a city in China. First, we separate the GPStraces of individual taxi drivers and link them with the revenuegenerated. Second, we investigate the taxi service strategies fromthree perspectives, namely, passenger-searching strategies, passen-ger-delivery strategies, and service-region preference. Finally, werepresent the taxi service strategies with a feature matrix andevaluate the correlation between service strategies and revenue,informing which strategies are efficient or inefficient. We predictthe revenue of taxi drivers based on their strategies and achieve aprediction residual as less as 2.35 RMB/h,1which demonstratesthat the extracted taxi service strategies with our proposed ap-proach well characterize the driving behavior and performanceof taxi drivers
In many cities, taxis are equipped with GPS devices, whichperiodically report to a central server the real-time informationabout the vehicle, including taxi locations and whether the taxiis occupied by a passenger. The collected GPS traces implicitlyconvey the service behaviors of the taxi drivers, includingwhere they pick up the passengers and how they find and deliverthe next passengers. These service behaviors vary from onedriver to another, depending on one’s service strategy in a givensituation. For example, after dropping off passengers, somedrivers may prefer to wait for new passengers at some familiarplaces, whereas others may prefer to search for new passengersin a busy area.The strategies employed by taxi drivers have a direct influ-ence on the amount of time and distance the taxi is occupied/vacant, resulting in differences in revenue, fuel consumption,and carbon emission. Good service strategies not only lead tohigh operating revenues but also improve efficiency of the entiretaxi service system and bring better services to passengers. Inaddition, good service strategies can help reduce carbon emis-sion by either decreasing the vacant/occupied driving distanceratio or selecting energy-efficient routes. Thus, understandingthe service strategies of taxi drivers can benefit the driversthemselves, passengers, and city planners https://srisivasakthitravels.com/
We investigate taxi drivers’ service strategies from threeperspectives: 1) passenger-searching strategies; 2) passenger-delivery strategies; and 3) service-area preference. Forpassenger-searching strategies, we group drivers’ preferenceinto three possible behaviors, namely,hunting locally, waitinglocally, and going distant (i.e., traveling to a distant loca-tion). For passenger-delivery strategies, we study their averagepassenger-delivery speed, which potentially reflects the drivers’ability to choose clearer routes when delivering passengers. Forservice-area preference, we study their preference of serviceareas in a city.
https://www.facebook.com/Sri-Siva-sakthi-Travels-102008227873939/
