K-Prototypes Segmentation Analysis on Large-Scale Ridesourcing Trip Data

Abstract

<jats:p> Shared mobility-on-demand services are expanding rapidly in cities around the world. As a prominent example, app-based ridesourcing is becoming an integral part of many urban transportation ecosystems. Despite the centrality, limited public availability of detailed temporal and spatial data on ridesourcing trips has limited research on how new services interact with traditional mobility options and how they affect travel in cities. Improving data-sharing agreements are opening unprecedented opportunities for research in this area. This study examined emerging patterns of mobility using recently released City of Chicago public ridesourcing data. The detailed spatio-temporal ridesourcing data were matched with weather, transit, and taxi data to gain a deeper understanding of ridesourcing’s role in Chicago’s mobility system. The goal was to investigate the systematic variations in patronage of ridehailing. K-prototypes was utilized to detect user segments owing to its ability to accept mixed variable data types. An extension of the K-means algorithm, its output was a classification of the data into several clusters called prototypes. Six ridesourcing prototypes were identified and discussed based on significant differences in relation to adverse weather conditions, competition with alternative modes, location and timing of use, and tendency for ridesplitting. The paper discusses the implications of the identified clusters related to affordability, equity, and competition with transit. </jats:p>

Investigating socio-spatial differences between solo ridehailing and pooled rides in diverse communities

“…Ensemble machine learning highlights the importance of pricing and timing variables for ride-pooling demand in Hangzhou, China (Chen et al, 2017). Clustering analysis on Chicago RH data reveals that pooled rides have distinct patterns, linked to affordability and local transit performance (Soria et al, 2020). These works shed light on the user trade-offs and aggregate demand patterns of ride-pooling.…”

“…To date, little is known about the current demand for pooled rides nor the determinants of use. Basic statistics are uncertain but suggest a market-share of pooling between 6 and 35 % (California Air Resource Board, 2019;Chen et al, 2018;Chicago Metropolitan Agency for Planning, 2019;Li et al, 2019;Lyft, 2018;Soria et al, 2020;Young et al, 2020). The hypothetical demand for pooling has been examined in stated preference work, finding that the addition of co-riders generates non-linear disutility in a shuttle setting and high sensitivity to time-cost trade-offs (Alonso-González et al, 2020).…”

“…To date there is limited understanding of how RH demand is shaped by different community contexts and the degree to which solo demand differs from pooling (Soria et al, 2020). More commonly, these modes are not differentiated.…”

Does Ridesourcing Respond to Unplanned Rail Disruptions? A Natural Experiment Analysis of Mobility Resilience and Disparity

“…Looking at broad spatial ridership patterns for the case of Chicago, research confirms a greater concentration of rides in the more affluent North and Central districts of the city (Brown, 2019b;Ghaffar et al, 2020;Soria et al, 2020). Fewer ridesourcing trips are generated in areas that are predominantly Hispanic or African American, lower income, or had lower rates of car ownership (Marquet, 2020).…”

“…In Chicago, Marquet (2020) finds that ridesourcing is used to travel between areas that are already highly accessible by transit, suggesting the potential to complement transit due to market density. Soria and Stathopoulos (2020) note that the link between ridesourcing and transit varies across cities and can be either competing or complementary, warranting continued research to pinpoint the evolving and location-specific mode connections. Overall, evidence indicates that ridesourcing is related to rider privilege and that most ridership takes place in the dense and accessible urban core (Lewis & MacKenzie, 2017;Soria & Stathopoulos, 2021).…”