Research on taxi drivers' passenger hotspot selecting patterns based on GPS data: A case study in Wuhan

Taxis are the most important components for public transit systems. The model of taxis is more flexible and convenient for passengers compared to other transit model like buses or railway. However, the dynamic of taxi locations will have influence on transit efficiency. Therefore, the hotspot selecting patterns when unoccupied with regards to different income level drivers were investigated in this study. Two month GPS data of 7200 taxis in Wuhan was used as the data samples. The Wuhan City was firstly Mapped Meshing and divided into 4623 grids. After preprocessing the taxi GPS data and taxi drivers' income level classification (top, ordinary and bottom), the pickup points were filtered and matched with all these grids. Heat and grid probability for passenger demand hotspot were proposed and analyzed in this study. The results showed that the correlation value between top drivers and heat are not always higher than ordinary taxi drivers but the correlation value between grid probability and top taxi drivers are always high at all time slots. The finding of this study reveals that the high income taxis drivers have the high ability for cruising to the closed hotspot having high grid probability compared with middle or low income drivers. It therefore recommended that, if such experience could be represented and learned by other taxi drivers, the efficiency of taxi transit systems will be improved. Furthermore, if the information of real time heat and grid probability of hotspot could be broadcasted to taxi drivers, it will be beneficial for taxi transit systems as well.

[1]  Chi-Chung Tao,et al.  Dynamic Taxi-Sharing Service Using Intelligent Transportation System Technologies , 2007, 2007 International Conference on Wireless Communications, Networking and Mobile Computing.

[2]  Yu-chin Tai,et al.  iTaxi : Context-Aware Taxi Demand Hotspots Prediction Using Ontology and Data Mining Approaches , 2010 .

[3]  Xia Yong,et al.  Analysis of Urban Traffic Based on Taxi GPS Data , 2014 .

[4]  Yong Sheng Zhang,et al.  Taxi Driver's Route Choice Behavior Analysis Based on Floating Car Data , 2013 .

[5]  Jane Yung-jen Hsu,et al.  Context-aware taxi demand hotspots prediction , 2010, Int. J. Bus. Intell. Data Min..

[6]  Xiaowei Hu,et al.  Exploring Urban Taxi Drivers’ Activity Distribution Based on GPS Data , 2014 .

[7]  Liqiu Meng,et al.  Understanding Taxi Driving Behaviors from Movement Data , 2015, AGILE Conf..

[8]  W Huber,et al.  EXTENDED FLOATING-CAR DATA FOR THE ACQUISITION OF TRAFFIC INFORMATION , 1999 .

[9]  Raghu K. Ganti,et al.  Analysis of Data from a Taxi Cab Participatory Sensor Network , 2011, MobiQuitous.

[10]  Fang Zong,et al.  Understanding Taxi Drivers’ Multi-day Cruising Patterns , 2015 .

[11]  Zhi-Hua Zhou,et al.  B-Planner: Planning Bidirectional Night Bus Routes Using Large-Scale Taxi GPS Traces , 2014, IEEE Transactions on Intelligent Transportation Systems.

[12]  Hartwig H. Hochmair SPATIO-TEMPORAL PATTERN ANALYSIS OF TAXI TRIPS IN NEW YORK CITY , 2015 .

[13]  Liqiu Meng,et al.  Getting in and out of a taxi: spatiotemporal hotspot analysis for floating taxi data , 2012 .

[14]  Xing Xie,et al.  T-drive: driving directions based on taxi trajectories , 2010, GIS '10.

[15]  Jie Cao,et al.  Pick-Up Tree Based Route Recommendation from Taxi Trajectories , 2012, WAIM.

[16]  Xing Xie,et al.  Where to find my next passenger , 2011, UbiComp '11.

[17]  Nicholas Jing Yuan,et al.  T-Finder: A Recommender System for Finding Passengers and Vacant Taxis , 2013, IEEE Transactions on Knowledge and Data Engineering.

[18]  Lin Sun,et al.  Understanding Taxi Service Strategies From Taxi GPS Traces , 2015, IEEE Transactions on Intelligent Transportation Systems.

[19]  Daqing Zhang,et al.  From taxi GPS traces to social and community dynamics , 2013, ACM Comput. Surv..

[20]  Xin Wang,et al.  Recommending Profitable Taxi Travel Routes Based on Big Taxi Trajectories Data , 2015, PAKDD.

[21]  Liang Liu,et al.  Uncovering cabdrivers' behavior patterns from their digital traces , 2010, Comput. Environ. Urban Syst..

[22]  Yu Zheng,et al.  T-share: A large-scale dynamic taxi ridesharing service , 2013, 2013 IEEE 29th International Conference on Data Engineering (ICDE).

[23]  João Gama,et al.  Predicting Taxi–Passenger Demand Using Streaming Data , 2013, IEEE Transactions on Intelligent Transportation Systems.

[24]  Xiao Liu,et al.  TaxiHailer: A Situation-Specific Taxi Pick-Up Points Recommendation System , 2014, DASFAA.