Putting Data in the Driver's Seat: Optimizing Earnings for On-Demand Ride-Hailing

ABSTRACT

On-demand ride-hailing platforms like Uber and Lyft are helping reshape urban transportation, by enabling car owners to become drivers for hire with minimal overhead. Although there are many studies that consider ride-hailing platforms holistically, e.g., from the perspective of supply and demand equilibria, little emphasis has been placed on optimization for the individual, self-interested drivers that currently comprise these fleets. While some individuals drive opportunistically either as their schedule allows or on a fixed schedule, we show that strategic behavior regarding when and where to drive can substantially increase driver income. In this paper, we formalize the problem of devising a driver strategy to maximize expected earnings, describe a series of dynamic programming algorithms to solve these problems under different sets of modeled actions available to the drivers, and exemplify the models and methods on a large scale simulation of driving for Uber in NYC. In our experiments, we use a newly-collected dataset that combines the NYC taxi rides dataset along with Uber API data, to build time-varying traffic and payout matrices for a representative six-month time period in greater NYC. From this input, we can reason about prospective itineraries and payoffs. Moreover, the framework enables us to rigorously reason about and analyze the sensitivity of our results to perturbations in the input data. Among our main findings is that repositioning throughout the day is key to maximizing driver earnings, whereas »chasing surge' is typically misguided and sometimes a costly move.

References

1. William A. Bailey Jr. and Thomas D. Clark Jr.. 1987. A simulation analysis of demand and fleet size effects on taxicab service rates Proceedings of the 19th Conference on Winter Simulation. ACM, 838--844.
2. Siddhartha Banerjee, Ramesh Johari, and Carlos Riquelme. 2015. Pricing in Ride-Sharing Platforms: A Queueing-Theoretic Approach. https://dl.acm.org/citation.cfm?id=2764527. Abstract appeared in ACM EC-2015.
3. Colin Camerer, Linda Babcock, George Loewenstein, and Richard Thaler. 1997. Labor Supply of New York City Cabdrivers: One day at a Time. The Quarterly Journal of Economics Vol. 112, 2 (1997), 407--441.
4. Juan Camilo Castillo, Dan Knoepfle, and Glen Weyl. 2017. Surge pricing solves the wild goose chase. In Proceedings of the 2017 ACM Conference on Economics and Computation. ACM, 241--242.
5. Harshal A. Chaudhari, John W. Byers, and Evimaria Terzi. 2017. Project Webpage: Putting Data in the Driver's Seat. https://www.bu.edu/cs/groups/dblab/ride-hailing. (2017).
6. Le Chen, Alan Mislove, and Christo Wilson. 2015. Peeking beneath the hood of Uber. In Proceedings of the 2015 ACM Internet Measurement Conference. ACM, 495--508.
7. M. Keith Chen and Michael Sheldon. 2016. Dynamic Pricing in a Labor Market: Surge Pricing and Flexible Work on the Uber Platform. http://www.anderson.ucla.edu/faculty_pages/keith.chen/papers/SurgeAndFlexibleWork_WorkingPaper.pdf. Working paper. Abstract appeared in ACM EC-2016.
8. The Rideshare Guy. 2016. Advice For New Uber Drivers- Don't Chase The Surge! http://maximumridesharingprofits.com/advice-new-uber-drivers-dont-chase-surge/. (2016).
9. Jonathan V. Hall and Alan B. Krueger. 2016. An Analysis of the Labor Market for Uber's Driver-Partners in the United States. Technical Report No. w22843. National Bureau of Economic Research.
10. Waster Hudson. 2016. Chasing the Surge: 3 Tips for Maximizing Uber Earnings. https://pjmedia.com/lifestyle/2016/07/19/chasing-the-surge-3-tips-for-maximizing-uber-earnings/1/. (2016).
11. Eric Jones, Travis Oliphant, Pearu Peterson, and others. 2001--2017. SciPy: Open source scientific tools for Python. (2001--2017). http://www.scipy.org/
12. Jaeyoung Jung, R. Jayakrishnan, and Ji Young Park. 2013. Design and Modeling of Real-time Shared-taxi Dispatch Algorithms Proc. Transportation Research Board 92nd Annual Meeting.
13. S. Kullback, M. Kupperman, and H. H. Ku. 1962. Tests for Contingency Tables and Markov Chains. Technometrics, Vol. 4, 4 (1962), 573--608.
14. Michal Maciejewski and Kai Nagel. 2013. Simulation and dynamic optimization of taxi services in MATSim. VSP Working Paper 13-0. TU Berlin, Transport Systems Planning and Transport Telematics, 2013 (2013).
15. Arnab Nilim and Laurent El Ghaoui. 2004. Robustness in Markov decision problems with uncertain transition matrices Advances in Neural Information Processing Systems. 839--846.
16. Jorge Nunes, Luís Matos, and António Trigo. 2011. Taxi Pick-Ups Route Optimization Using Genetic Algorithms. Adaptive and Natural Computing Algorithms (2011), 410--419.
17. Erhun Ozkan and Amy R. Ward. 2016. Dynamic Matching for Real-time Ridesharing. https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2844451, (2016). Working paper.
18. Ying Shi and Zhaotong Lian. 2016. Optimization and strategic behavior in a passenger--taxi service system. European Journal of Operational Research Vol. 249, 3 (2016), 1024--1032.
19. The New York Times. 2015. An App That Helps Drivers Earn the Most From Their Trips. https://www.nytimes.com/2015/05/10/technology/a-dashboard-management-consultant.html. (2015)
20. The New York Times. 2017. How Uber Uses Psychological Tricks to Push Its Drivers' Buttons. https://www.nytimes.com/interactive/2017/04/02/technology/uber-drivers-psychological-tricks.html. (2017).
21. Wikipedia. 2017. Skellam distribution -- Wikipedia, The Free Encyclopedia. https://en.wikipedia.org/w/index.php?title=Skellam_distribution. (2017).
22. Hai Yang, Sze Chun Wong, and Ki Wong. 2002. Demand--supply equilibrium of taxi services in a network under competition and regulation. Transportation Research Part B: Methodological, Vol. 36, 9 (2002), 799--819.

Index Terms

• Information systems

  • Information systems applications

    • Data mining