Uber vs. Taxis: Event detection and differentiation in New York City

Abstract

GIScience 2016 Short Paper Proceedings Uber vs. Taxis: Event detection and differentiation in New York City Grant McKenzie 1 , Carlos Ba´ez 2 Department of Geographical Sciences, University of Maryland, College Park, USA 2 Department of Geography, University of California, Santa Barbara, USA Email: gmck@umd.edu; carlos.baez@geog.ucsb.edu Abstract The recent rise of ride-sourcing services such as Uber have significantly changed the transportation landscape. This work takes a first step in di↵erentiating Uber and taxi transportation methods through events attended by their passengers. Using a sample of Uber and taxi pick-up times and locations in New York City, we show that events can be detected within each platform. Through identification of a select few of these events, this work takes a preliminary step in showing that there is a di↵erence in the types of events that are attended by Uber users and taxi passengers. 1. Introduction Historically, taxicab companies have controlled the largest share of the for-hire vehi- cle (FHV) market in the United States. Over the past few years, however, alternative transportation options have arisen such as Uber and Lyft that rely on the use of online- enabled platforms to connect passengers with drivers. Together with others, these types of ride-sourcing companies, often called Transportation Network Companies(TNC), have significantly disrupted the traditional transport model, namely taxi service. By some accounts (Certify, 2015), TNCs now account for 46% of some U.S.-based FHV markets. This dramatic shift in the means of transportation has spurred a lot of research and discussion on its impact and significance (NRC-TRB, 2015; Hall et al., 2015). From a spatiotemporal research perspective, this shift has also lead to some important questions related to the di↵erences between these services as well as the people that use them. This short paper presents a first step in exploring the di↵erences between traditional taxi services and TNCs as described through events 1 in New York City. Specifically, this work addresses the following research questions. • Is it possible to detect events based on passenger pick-up times and locations in publicly available Uber and taxi data? • Do events detected in the Uber dataset di↵er from those detected in the taxi dataset? • Do these findings support existing research showing that there are di↵erences between TNC users and taxi riders? We approach this question through identifying a select sample of detected events. As stated in this last question, existing work in this area indicates that there are di↵erences in the demographics of taxi and TNC passengers. Specifically, TNC user surveys suggest that, relative to taxi users, TNC passengers are younger and posses a higher average level of education (Rayle et al., 2016). Our work continues on this See work by Worboys (2005) in discussing and defining events.