Conference Proceeding Article
Nowadays, there are many taxis traversing around the city searching for available passengers, but their hunts of passengers are not always efficient. To the dynamics of traffic and biased passenger distributions, current offline recommendations based on place of interests may not work well. In this paper, we define a new problem, global-optimal trajectory retrieving (GOTR), as finding a connected trajectory of high profit and high probability to pick up a passenger within a given time period in real-time. To tackle this challenging problem, we present a system, called HUNTS, based on the knowledge from both historical and online GPS data and business data. To achieve above objectives, first, we propose a dynamic scoring system to evaluate each road segment in different time periods by considering both picking-up rate and profit factors. Second, we introduce a novel method, called trajectory sewing, based on a heuristic method and the Skyline technique, to produce an approximate optimal trajectory in real-time. Our method produces a connected trajectory rather than several place of interests to avoid frequent next-hop queries. Third, to avoid congestion and other real-time traffic situations, we update the score of each road segment constantly via an online handler. Finally, we validate our system using a large-scale data of around 15,000 taxis in a large city in China, and compare the results with regular taxis’ hunts and the state-of-the-art.
Databases and Information Systems
MDM '13 Proceedings of the 2013 IEEE 14th International Conference on Mobile Data Management
DING, Ye; LIU, Siyuan; PU, Jiansu; and NI, Lionel.
HUNTS: A Trajectory Recommendation System for Effective and Efficient Hunting of Taxi Passengers. (2013). MDM '13 Proceedings of the 2013 IEEE 14th International Conference on Mobile Data Management. 1, 107-116. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/3472
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.