ABSTRACT
The ever-growing popularity of taxi services in modern cities creates the demand for making taxi activities more efficient. Specifically, the main aims are reducing the cruising time of taxi when drivers hunt for new passengers and maximize potential profit for the next trip, which attracts many interest of researchers. However, most research use historical GPS tracks without considering 1) the data of current day, especially a few last hours from the current time and 2) completely ignore the road-passengers (traditional passengers who hail taxi on road), which account for a large portion of taxi demand in reality. To overcome such drawbacks, we propose DTA hunter system, incorporating such information into a statistical model by vectorizing historical data and probability equations respectively. The final aim of the model is that given a taxi information (current location & time), it will suggest k parking places and optimal paths to get there that maximize the probability of picking up new passengers and the expected distance of next trip. We evaluate the model with taxi services dataset of Vietnam VinaSun Taxi Company in 4 weeks (from 18/10/2015 to 14/11/2015) and the result of our model (the probability of picking up new passengers in the future) is better than the daily behavior of taxi drivers in reality.
- Sotiris Brakatsoulas, Dieter Pfoser, Randall Salas, and Carola Wenk. 2005. On map-matching vehicle tracking data. In Proceedings of the 31st international conference on Very large data bases. VLDB Endowment, 853--864. Google ScholarDigital Library
- Han-wen Chang, Yu-chin Tai, and Jane Yung-jen Hsu. 2009. Context-aware taxi demand hotspots prediction. International Journal of Business Intelligence and Data Mining 5, 1 (2009), 3--18. Google ScholarDigital Library
- Bill de Blasio. 2016. 2016 TLC Factbook. (2016). http://www.nyc.gov/html/tlc/html/about/factbook.shtmlGoogle Scholar
- J. L. Deng. 1989. Introduction to Grey System Theory. J. Grey Syst. 1, 1 (Nov. 1989), 1--24. http://dl.acm.org/citation.cfm?id=90757.90758 Google ScholarDigital Library
- David Eppstein. 1998. Finding the k shortest paths. SIAM J. Comput. 28, 2 (1998), 652--673. Google ScholarDigital Library
- Martin Ester, Hans-Peter Kriegel, Jörg Sander, Xiaowei Xu, et al. 1996. A density-based algorithm for discovering clusters in large spatial databases with noise.. In Kdd, Vol. 96. 226--231. Google ScholarDigital Library
- Chang Yang Huigui Rong, Xun Zhou. 2016. The Rich and the Poor: A Markov Decision Process Approach to Optimizing Taxi Driver Revenue Efficiency. CIKM '16 (2016).Google ScholarDigital Library
- Hui Zheng Huigui Rong, Zepeng Wang. 2017. Mining efficient taxi operation strategies from large scale geo-location data. IEEE Access PP (July 2017), 1--1. http://ieeexplore.ieee.org/document/7995029/Google Scholar
- Ren-Hung Hwang, Yu-Ling Hsueh, and Yu-Ting Chen. 2015. An Effective Taxi Recommender System Based on a Spatio-temporal Factor Analysis Model. Inf. Sci. 314, C (Sept. 2015), 28--40. Google ScholarDigital Library
- Jason W. Powell, Yan Huang, Favyen Bastani, and Minhe Ji. 2011. Towards Reducing Taxicab Cruising Time Using Spatio-temporal Profitability Maps. In Proceedings of the 12th International Conference on Advances in Spatial and Temporal Databases (SSTD'11). Springer-Verlag, Berlin, Heidelberg, 242--260. http://dl.acm.org/citation.cfm?id=2035253.2035273 Google ScholarDigital Library
- Meng Qu, Hengshu Zhu, Junming Liu, Guannan Liu, and Hui Xiong. 2014. A Cost-effective Recommender System for Taxi Drivers. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '14). ACM, New York, NY, USA, 45--54. Google ScholarDigital Library
- Nicholas Jing Yuan, Yu Zheng, Liuhang Zhang, and Xing Xie. 2013. T-Finder: A Recommender System for Finding Passengers and Vacant Taxis. IEEE Trans. on Knowl. and Data Eng. 25, 10 (Oct. 2013), 2390--2403. Google ScholarDigital Library
Index Terms
DTA Hunter System: A new statistic-based framework of predicting future demand for taxi drivers
Recommendations
STIETR: Spatial-temporal Intelligent E-Taxi Recommendation System Using GPS Trajectories
GeoAI '19: Proceedings of the 3rd ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge DiscoveryE-taxies (ETs) are facing great challenges such as short driving range, long charging time and sparse charging stations, thus hamper its acceptance by fuel taxi drivers. This study presents a novel spatial-temporal intelligent recommendation system for ...
An efficient algorithm for taxi system optimization
AAMAS '14: Proceedings of the 2014 international conference on Autonomous agents and multi-agent systemsTaxi service is an important mode of modern public transportation. However, operated by a large number of self-controlled and profit-driven taxi drivers, taxi systems are quite in efficient and difficult to analyze and regulate. While there has been ...
Optimizing Efficiency of Taxi Systems: Scaling-up and Handling Arbitrary Constraints
AAMAS '15: Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent SystemsTaxi service is an indispensable part of public transport in modern cities. However, due to its decentralized operation mode, taxi services in many cities are inefficient. Besides, the decentralized nature also poses significant challenges to analyzing ...
Comments