Transportation Network Companies Research Articles

Mobility Energy Productivity Evaluation of On-Demand Transit: A Case Study in Arlington, Texas

On-demand transit (ODT) systems are increasing in number and size. To evaluate and quantify outcomes, the research team utilizes the mobility energy productivity (MEP) metric, which is a holistic accessibility measure, to analyze and compare the mobility of various transportation modes in Arlington, Texas. The MEP tool is applied to the ODT system in Arlington, Texas, as well as to five existing transportation modes (driving, transportation network company, transit, biking, and walking). Six ODT scenarios are also analyzed and compared. The analysis is focused on the opportunities that an ODT system presents for transportation disadvantaged communities (DACs) with low rates of car ownership. Although driving received the highest MEP score—a finding typical for a U.S.A. city— the results for the ODT system reveal that it serves those in DACs effectively, helping to achieve an equity design goal. ODT improved the average MEP score across the service area by 83% when considering only accessible, nonprivate vehicle modes (biking, transit, and ODT). For the ODT scenarios, decreasing the wait time by 50% compared with the baseline scenario led to a nearly 160% increase in the MEP score, whereas increasing the ODT travel speed by 21% led to an 80% improvement in the MEP score. As analyzed through the MEP tool, this paper demonstrates how ODT can enhance mobility, particularly for DACs. The results of an MEP analysis can be used by researchers and transit agencies to compare transportation modes and improve the effectiveness of transportation systems across a service area.

Greenhouse Gas Emissions and Potential for Electrifying Transportation Network Companies in Toronto

This study investigates the spatial and temporal patterns of greenhouse gas (GHG) emissions from transportation network companies (TNCs) in Toronto, Canada. TNC services primarily consist of short-distance trips in the central business district. Deadheading—driving without passengers—contributes 40% of TNC GHG emissions, and part-time drivers had a higher deadheading proportion than full-time drivers. Pooled TNC trips account for 10% of total trips, and just 27% of pooled trips resulted in multiple passengers sharing a vehicle on the same route. The GHG implications of pooled trips were compared with other TNC services and with a consumer driving their own private vehicle, through the estimation of median trip emission intensities of each TNC service in grams of CO2eq per passenger-km, while accounting for deadheading. Non-pooled internal combustion engine (ICE) ride-hailing trips have a median emission intensity 61% higher than that of a single-occupancy private vehicle. The median emission intensity for a pooled ICE ride-hailing trip is 20% higher than that of driving one’s own vehicle. Vehicle electrification provides a 91% daily GHG emission reduction for this fleet. This reduction is mainly achieved through full-time drivers, who, on average, achieve three times as much GHG savings per electrified vehicle compared with part-time drivers.

Design and analysis of ride-sourcing services with auxiliary autonomous vehicles for transportation hubs in multi-modal transportation systems

Autonomous vehicles (AVs), which can be fully controlled by remote/online operators, could be an extension of ride-sourcing services provided by transportation network companies (TNCs). Meanwhile, substitutive and complementary relationships between ride-sourcing and public transit could also help TNCs increase their profit under certain strategies. Unlike previous studies that generally ignored either AVs or interactions between public transit and ride-sourcing, we introduce AV-involved operational strategies into a multi-modal system. In this paper, we focus on transportation hubs in an urban area and let the TNC assign AVs to these hubs for serving only within that particular hub at a differentiated fare; meanwhile, passengers could choose among AVs, human-driven vehicles (HVs), combined modes with public transit and AVs or HVs, or other travel modes to fulfill their travel needs. We develop a mathematical model to investigate the impacts of such an operational strategy, and formulate an optimisation problem to maximise the TNC's profit and minimise total waiting time simultaneously by adjusting AV fare and fleet size. We further propose a comprehensive modeling framework with the analytical model, optimisation problem, calibration method, and heuristic algorithm, making it a general approach for different real-world scenarios. Following the framework, we conduct a case study based on real-world datasets of public transit and ride-sourcing services in Hangzhou, China. Different market schemes are analyzed and compared with the currently existing situation. The results demonstrate that by adopting this auxiliary-AV-oriented operational strategy, the TNC's profit and public transit ridership can both be increased, and passengers could enjoy a shorter waiting time for HV ride-sourcing trips. Moreover, the TNC is more inclined to allocate more AVs to hubs with large commute needs and uncongested traffic, leading to a high profit for the TNC and a short waiting time for passengers. Societal preferences towards AV trips are also analyzed. The results provide in-depth references for real-world AV-related ride-sourcing operational problems.

Using Online Videos to Improve Attitudes toward Shared Autonomous Vehicles: Age and Video Type Differences

Future adoption of shared automated vehicles (SAVs) should lead to several societal benefits, but both automated vehicles (AVs) and ridesharing must overcome their barriers to acceptance. Previous research has investigated age differences in ridesharing usage and factors influencing the acceptability and acceptance of AVs. Further complicating our understanding of SAV acceptance, much of the public lack accurate knowledge and/or actual experience regarding AVs. In this study, we employed a 3 (age group) × 4 (video condition) longitudinal mixed experimental design to investigate age differences in anticipated SAV acceptance after viewing different types of introductory videos related to AVs (educational, experiential, or both) or currently available ridesharing provided by transportation network companies (control). Younger, middle-aged, and older adults were randomly assigned to watch (1) an educational video about SAV technologies and potential benefits, (2) an experiential video showing an SAV navigating traffic, (3) both the experiential and educational videos or (4) a control video explaining how current ridesharing services work. Attitudes toward SAVs (intent to use, trust/reliability, perceived usefulness, perceived ease of use, safety, desire for control, cost, authority, media, and social influence) were measured before and after viewing the video(s). Significant differences in how SAV attitudes changed were found between the educational and experiential video conditions relative to the control video and between different age groups. Findings suggest that educational and/or experiential videos delivered in an online format can have modest but significant improvements to their viewers’ attitudes toward SAVs—particularly those of older adults.

Enhancing Demand Prediction: A Multi-Task Learning Approach for Taxis and TNCs

Taxis and Transportation Network Companies (TNCs) are important components of the urban transportation system. An accurate short-term forecast of passenger demand can help operators better allocate taxi or TNC services to achieve supply–demand balance in real time. As a result, drivers can improve the efficiency of passenger pick-ups, thereby reducing traffic congestion and contributing to the overall sustainability of the program. Previous research has proposed sophisticated machine learning and neural-network-based models to predict the short-term demand for taxi or TNC services. However, few of them jointly consider both modes, even though the short-term demand for taxis and TNCs is closely related. By enabling information sharing between the two modes, it is possible to reduce the prediction errors for both. To improve the prediction accuracy for both modes, this study proposes a multi-task learning (MTL) model that jointly predicts the short-term demand for taxis and TNCs. The model adopts a gating mechanism that selectively shares information between the two modes to avoid negative transfer. Additionally, the model captures the second-order spatial dependency of demand by applying a graph convolutional network. To test the effectiveness of the technique, this study uses taxi and TNC demand data from Manhattan, New York, as a case study. The prediction accuracy of single-task learning and multi-task learning models are compared, and the results show that the multi-task learning approach outperforms single-task learning and benchmark models.

Customer Choice of Different Types of Non-Autonomous and Autonomous Transportation Network Company Services in the San Francisco Bay Area

In recent years, transportation network companies (TNCs) have grown rapidly. However, with the high intensity of competition caused by multi-homing and low switching costs, providers like Uber and Lyft have yet to achieve profitability. Following the winner-takes-all theory, providers fight for market dominance with price wars and incentives, expecting to achieve profitability once they gain market power. However, despite extensive research on why customers use TNCs instead of other modes, there is limited research on customer choice between competing TNCs. This study examines how customers choose among competing providers and service options for booking rides, considering the influence of service characteristics. The research questions are answered for the San Francisco Bay Area, various TNC and autonomous TNC (ATNC) services (Basic, Green, Premium, and Pool), and use cases based on time urgency and trip purpose. For this, we conducted a choice-based conjoint (CBC) analysis with 1,415 participants. Results indicate that an almost equal number of customers choose services based on loyalty or habit as those customers who switch services based on better waiting times or prices. The results confirm the importance of provider size on customer choice and indicate a high time- and price-sensitivity of customers. On average, Green services are most preferred, followed by Basic, Premium, and Pool. When comparing TNC and ATNC services, customers are positive toward autonomous services but require lower prices to switch. These findings contribute to the understanding of customer choice in competitive TNC and future ATNC markets, with relevance for both theory and practitioners.

Exploration of Factors That Influence Willingness to Consider Pooled Rideshare

Ridesharing has become an increasingly prevalent form of transportation. Although transportation network companies such as Uber and Lyft initially started as a personal rideshare service where individuals ride alone or with people they know, rideshare services have been expanded to pooled rideshare—a dynamic rideshare system where an individual rides with passengers they do not know. Despite the growth in rideshare services worldwide, the use of pooled rideshare in the U.S.A. is relatively low compared to other forms of transportation. A national U.S. survey ( N = 5385) was conducted to investigate reasons why individuals are willing or unwilling to consider pooled rideshare. Exploratory and confirmatory factor analyses were performed, where the exploratory factor analysis suggests five factors, specifically, service experience, time/cost, traffic/environment, privacy, and safety. Model fit indices of the confirmatory factor analysis verified that these five factors can represent the factors behind riders’ willingness to consider pooled rideshare. Furthermore, a binomial logistic regression was conducted to explore how the five factors influence riders’ willingness to consider pooled rideshare. The three factors that influence riders’ willingness to consider pooled rideshare were service experience ( B = 1.05), traffic/environment ( B = .38), and time/cost ( B = .26), while a lack of privacy ( B = −1.46) can be a deterrent for pooled rideshare. Safety is important for those who are both willing and unwilling to consider the use of pooled rideshare. Understanding these factors is important for the future of pooled rideshare services in the U.S.A.

An exact second order cone programming approach for traffic assignment problems

Demographic changes, urbanization and increasing vehicle ownership at unprecedented rates put a lot of strain on cities particularly on urban mobility and transportation and overwhelm transportation network infrastructures and current transportation systems, which are not built to cope with such a fast increasing demand. Traffic congestion is considered as the most difficult challenge to tackle for sustainable urban mobility and is aggravated by the increased freight activity due to e-commerce and on-demand delivery and the explosive growth in transportation network companies and ride-hailing services. There is a need to implement a combination of policies to ensure that increased urban traffic congestion does not lower the quality of life and threaten global climate and human health and to prevent further economic losses. This study aims to contribute to the United Nations (UN) climate action and sustainable development goals in tackling recurring traffic congestion problem in urban areas to achieve a sustainable urban mobility in that it offers a solution methodology for traffic assignment problem. We introduce an exact generalized solution methodology based on reformulation of existing traffic assignment problems as a second order cone programming (SOCP) problem and propose column generation (CG) and cutting plane (CP) algorithms to solve the problem effectively for large scale road network instances. We conduct numerical experiments to test the performance of the proposed algorithms on realistic road networks.

Exploring the differences between express and ride-pooling: A dual perspective on user perception and functional positioning in urban traffic system

Ride-hailing services, alongside public transportation (subway and bus), active modes (bike-sharing and walking), and private cars, are collectively reshaping urban transportation systems worldwide. However, the differences in user risk perception and functional positioning among different ride-hailing services, especially express and ride-pooling, are not yet clear. The study, conducted in Nanjing, China, designed two stated-preference questionnaires to assess the substitutability and complementarity of express and ride-pooling services. Four latent variables were introduced to quantify user risk perception: time risk, economic risk, service risk, and safety risk. The Integrated Choice and Latent Variable model used in this study is based on the Mixed Nested Logit model, which focuses more on the interdependence among different travel modes, as well as individual heterogeneity, compared with traditional logit models. The research findings indicate that in terms of risk perception, ride-hailing users have stronger service risk perception, weaker time risk perception, and weaker safety risk perception compared with public transportation users. Furthermore, compared with ride-pooling users, express users have stronger time risk perception and weaker economic risk perception. From a functional positioning perspective, ride-pooling services complement public transportation systems, while express services are preferred for long-distance door-to-door travel. Based on the research findings, this study offers a set of recommendations to support the sustainable growth of Transportation Network Companies (TNCs), guide government regulatory efforts, and explore opportunities for collaboration between the TNCs and government agencies, aiming to foster the robust development of urban transportation systems.

Platforms, Politics, and Policy Change: Framing A Governance Approach to TNCs in the Gig Economy

In social science, platform capitalism is becoming more analyzed as digital app-based platforms have revolutionized the global exchange of goods and services, prompting multifaceted challenges within society, economics, and politics. Platform governance emerges as this changing landscape unfolds, illuminating the intricate interplay between national and local regulatory frameworks and the burgeoning power dynamics among diverse stakeholders. This article provides a framework for examining the complex political and governance issues that have surfaced in the gig economy, mainly focused on the proliferation of ride-hailing platforms, such as Uber, also known as Transportation Network Companies (TNCs). This article examines the framework of platform governance contributing theoretically by putting into dialogue a literature primarily focused on studying social media with another branch of the platform society in which policy disruption has been evident, such as transportation and urban mobility. The analysis focuses on three fundamental dimensions of political economy: ideas, interests, and institutions. The paper also reviews how these three approaches have operated in recent scholarly literature. Finally, the article underscores the need for future research to address this complexity from a contingent approach to promote a comprehensive understanding of platform regulation.

Spatiotemporal Heterogeneous Effects of Built Environment and Taxi Demand on Ride-Hailing Ridership

Researchers have applied a series of global models to investigate the link between the built environment and ride-hailing ridership based on ride-hailing data from one specific transportation network company (TNC). However, these research designs inadequately represent real ride-hailing demand within a specific spatial range and cannot reflect spatiotemporal heterogeneity in the link. For the first time, this study collects all demand data of TNCs in Nanjing and analyzes their relationship with the built environment. The effect of taxi demand is considered. We adopt a multiscale geographically weighted regression model to account for the spatial non-stationarity and the multiscale effect of each built environment variable. The findings reveal spatiotemporal heterogeneous relationships of the built environment with ride-hailing ridership. Although the relationship between taxi and ride-hailing ridership varies across spatial locations, ride-hailing always acts as a cooperator for traditional taxis. The findings provide implications for policy making, urban planning, and travel demand management of ride-hailing.

Charging autonomous electric vehicle fleet for mobility-on-demand services: Plug in or swap out?

This paper compares two prevalent charging strategies for electric vehicles, plug-in charging and battery swapping, to investigate which charging strategy is superior for electric autonomous mobility-on-demand (AMoD) systems. To this end, we use a queueing-theoretic model to characterize the vehicle waiting time at charging stations and battery swapping stations, respectively. The model is integrated into an economic analysis of the electric AMoD system operated by a transportation network company (TNC), where the incentives of passengers, the charging/operating shift of TNC vehicles, the operational decisions of the platform, and the planning decisions of the government are captured. Overall, a bi-level optimization framework is proposed for charging infrastructure planning of the electric AMoD system. Based on the proposed framework, we compare the socio-economic performance of plug-in charging and battery swapping, and investigate how this comparison depends on the evolving charging technologies (such as charging speed, battery capacity, and infrastructure cost). At the planning level, we find that when choosing plug-in charging, increased charging speed leads to a transformation of infrastructure from sparsely distributed large stations to densely distributed small stations, while enlarged battery capacity transforms the infrastructure from densely distributed small stations to sparsely distributed large stations. On the other hand, when choosing battery swapping, both increased charging speed and enlarged battery capacity will lead to a smaller number of battery swapping stations. At the operational level, we find that improved charging speed leads to increased TNC profit when choosing plug-in charging, whereas improved charging speed may lead to smaller TNC profit under battery swapping. The above insights are validated through realistic numerical studies.

Merging transport network companies and taxis in Curitiba’s BRT system

AbstractThe Brazilian city of Curitiba became known around the world for pioneering bus rapid transit (BRT) in the 1970s. Five decades later, public transport ridership is declining on the city’s bus-based system. One-person car trips and car ownership are soaring, and services provided by transport network companies rapidly proliferate and then disappear as congestion worsens and expands across the road network. This was the macro-scale scenario for mobility and modal trends in Curitiba until COVID-19 brought things to a screeching halt in 2020. The widespread use of information and communication technologies has allowed taxi and car ride-hailing transport network schemes to emerge while blurring the lines between public and private and individual and collective transport, locally as well as globally. In 2016, transport network company systems, apps, private cars, services, drivers and passengers disrupted Curitiba’s longstanding and well-regulated taxi system and market for licenses. In 2023, hailing a cab or a shared ride feels and costs the same for passengers (now customers). This study investigates whether these actors and technologies compete with or complement each other in this city, locating and quantifying the benefits for passengers of merging taxi and car ridesharing with the BRT system as first- and last-mile transport to and from BRT corridors. We developed mobile information and communication technologies and acquired, processed, and analyzed millions of data points for passenger location on BRT, ordinary bus, and taxi trips at the city scale. The shareability index for Curitiba’s taxi or car rides was calculated, demonstrating that 60% of all taxi trips have the potential to serve as first- and last-mile transport solution to and from the BRT terminals, stations, and corridors and that nearly 40% of taxi trips both originate and end near (< 500 m) this BRT system infrastructure. By envisioning how transport network companies could merge into the built environment thanks to urban transport digitization, we have developed a model for integrating public transport with the analytic framework of transport network companies that could be deployed in other cities with similar challenges related to public transport, sociotechnical arrangements, system complexity, policymaking, and planning.

Understanding market competition between transportation network companies using big data

As in a typical two-sided market, the competition between transportation network companies (TNCs) can lead to market fragmentation and loss of matching efficiency between passengers and drivers, whereas a monopoly market may result in the dominant TNC abusing its market power. Therefore, whether to encourage or discourage competition between TNCs is a debatable question for cities. Prior studies explored this question mostly through mathematical equilibrium models, but few have comprehensively investigated it based on empirical analysis using real-world data. To fill this gap, this study proposes a framework to measure and analyze the competition between TNCs using the most accessible ride-hailing trip data. Specifically, using an interpretable machine learning model, we investigate how TNCs’ pricing and wage strategies influence their market shares and how competition intensity affects passenger cost and driver income. The results based on large-scale trip records from four TNCs in New York City show that the pricing strategy is more influential than the wage strategy on the market shares and competition intensity. Instead of the top TNC, it is the strategies of challenger TNCs (with sizeable but not the biggest market shares) that affect the competition more. Both the passenger cost and driver income can benefit from competition even after considering the potential loss of matching efficiency, while TNCs’ profits shrink with growing competition intensity. These findings suggest that cities should encourage competition between TNCs, yet within a limit. They add empirical evidence to prior studies and provide implications for regulating TNC competition.

What stay-at-home orders reveal about dependence on transportation network companies

AbstractTransportation Network Companies (TNC) such as Uber and Lyft set out to provide transportation not fulfilled by private vehicles or public transit. The social value of TNCs for essential trips (i.e., necessary trips that cannot be fulfilled by another mode of transportation) is difficult to discern in normal conditions. The COVID-19 stay-at-home order is used as a natural experiment to investigate the heterogeneous ability to avoid TNCs by income areas of trip origins. We measure the sensitivity of different populations’ ability to respond to policies and to avoid TNC trips (e.g., early stay-at-home orders) using a difference-in-difference style regression. Previous studies have indicated that under normal conditions TNCs primarily serve high-income areas, indicating that TNCs may not be improving transportation equity but instead serve as an additional mode of transportation for passengers with multiple options. We fill a gap in the literature by evaluating the role TNCs play in serving unavoidable and essential trips. We find that high-income community areas showed greater sensitivity to the stay-at-home order with a 56% greater decrease in TNC ridership during the stay-at-home order compared to low-income community areas. Specifically, TNC trips from high-income areas decreased by 80%. This indicates that although riders from high-income community areas might make up the majority of trips in normal conditions, low-income community areas are less able to adapt to stay-at-home orders because of a higher degree of non-flexible and essential jobs or less access to TNC alternatives like private vehicles and public transit.

Driving sustainable transportation: insights and strategies for shared-rides services

The concept of sharing, enabled by emerging technologies, is playing an increasingly important role in contributing to a transformation toward more sustainable transportation. This study aimed to contribute to the growing body of literature on on-demand transportation services, with a particular emphasis on sharing or pooling a ride when using services such as transportation-network companies (TNCs) and microtransit. The study conducted a shared mobility survey of over 2,500 respondents from selected locales across Texas—ranging from large urban areas to small cities and rural areas. We analyzed the survey data in detail using extensive statistical analysis and inferential techniques and adopted an analysis approach toward implementation-oriented research to address the gap between theory and practice. Demographic, as well as geographic and built-environment, factors were found to play an important role in determining whether users will opt for a shared or pooled service and/or how they perceive these alternatives. The findings highlight the importance of improving safety and security, increasing awareness of the benefits of ride-sharing, and designing appropriate policy measures to promote sustainable mobility. We identified potential operational improvements, government policies, and employer programs to improve shared-ride services and encourage their use, such as reducing uncertainty in shared rides and minimizing inconvenience for passengers. A critical finding was the need to prioritize operational improvements in shared-ride trips over solely relying on financial incentives to induce behavior change. Enhanced public awareness and education were also determined to be crucial regardless of the nature of improvements, policies, or programs that are implemented.

Effects of the COVID-19 pandemic on use and perception of shared e-scooters

Micro-mobility, such as electric scooters (e-scooters) and bicycles, has gained attraction in recent years by offering reduced emissions, decreased congestion, and improved public health. However, due to the COVID-19 pandemic, travel behavior and mode choices have changed. As such, shared micro-mobility are likely more vulnerable to these changes, as a relatively new mode, with less habitual riders and their shared nature perceived as a higher risk. The objective of this paper is to understand how preferences and perceptions of micro-mobility changed before, during, and potentially after the pandemic, and relative to quarantine behavior. Shared e-scooter trip data (N = 2604) before and during the pandemic, and survey data (N = 134) during the pandemic, were collected in one small- to mid-sized US city. Number of e-scooter trips decreased while duration of trips increased during the pandemic. People who only left their houses for essential activities and/or work reported using public transit and transportation network companies (e.g., Uber) significantly less during the pandemic, but there was no association between their use of micro-mobility and timeframes of the pandemic. People who left their houses similar to before the pandemic did not significantly change their mode choices during the pandemic. Most respondents were neutral in opinion about sanitary levels of shared micro-mobility, suggesting an opportunity to attract riders through new hygiene initiatives. Micro-mobility operators and jurisdictions can use these insights on perception and use of shared transport modes as travel behavior adjusts post pandemic.

Going My Way? Understanding Curb Management and Incentive Policies to Increase Pooling Service Use and Public Transit Linkages in the San Francisco Bay Area

Despite lower user costs, only 20% to 40% of transportation network company (TNC) users select a pooled, or shared, ride option. Why are existing TNC users not selecting the pooled option or using TNCs to connect to public transit, and what role do built environment features and incentives play in their decision? This study explores the factors that influence TNC user decisions through a multi-method approach comprising photovoice small group discussions and a workshop. Between March 2021 and May 2021, 15 San Francisco Bay Area TNC users shared photographs they took of TNC pick-up locations through two-to-three-person guided small group discussions. The photos revealed that users prefer waiting in retail or in well-lit, good-visibility locations. Participants’ primary concern was personal safety, particularly female users who may take additional precautions when walking to pick-up locations and waiting for and taking rides. In July 2021, 12 photovoice participants and 5 stakeholders provided feedback on key findings from the photography discussions. The pooling improvement strategies identified include the following: designated TNC stops with lighting and marked pick-up areas; enhanced in-app safety features; TNC partnerships with employers and retailers to incentivize riders; and mode transfer discounts for connecting TNCs to public transit. The findings suggest that safety related to the built environment plays an outsized role in a TNC user’s decision to pool or connect to public transit, and the out-of-vehicle portion of the TNC trip should be equally considered when developing policies to increase pooling.

Region-Aware Hierarchical Graph Contrastive Learning for Ride-Hailing Driver Profiling

Driver profiling, which is the process of extracting driver preferences and behavioral patterns from collected driving data, can be performed on a microscopic or macroscopic scale. Microscopic driver profiling, which uses onboard data, can be incorporated into advanced driver assistance systems or used by insurance companies to implement pay-as-you-drive programs. However, transportation network companies (TNCs) typically cannot access onboard data owing to privacy and cost concerns. Therefore, TNCs typically perform macroscopic driver profiling using the raw GPS trajectories generated by smartphones. Accurate profiling of ride-hailing drivers can enhance the user experience and order dispatching process by allowing the TNCs to accurately predict various downstream tasks such as time of arrival of rides. Notably, most of the approaches that use raw GPS trajectories for driver profiling directly leverage trajectory data without any comprehensive analysis, resulting in neglect of the rich regional semantic information and underlying correlations among trajectories. Therefore, we study the ride-hailing driver profiling problem and propose a Hierarchical Graph Contrastive Learning (HGCL) framework that can automatically learn low-dimensional embeddings encoding driver behaviors from raw GPS data. The HGCL framework consists of a hierarchical graph neural network for capturing the regional features of trajectories and a hierarchical contrastive learning strategy aimed at learning high-quality representations at different levels. The effectiveness of the proposed model is evaluated using driver representation embeddings learned from a real-world large-scale dataset for three downstream tasks. The results of extensive experiments demonstrate the efficacy of the proposed HGCL framework for driver profiling.

Managing ridesharing with incentives in a bottleneck model

Ridesharing is recognized as an environmentally friendly alternative to daily transportation that can potentially reduce vehicular carbon emissions. Transportation Network Companies (TNC) have been providing ridesharing services. However, generalized costs need to be balanced between rideshare drivers and passengers via financial instruments to reach a sustainable equilibrium. In this paper, we demonstrate the effectiveness of Incentive-Based Travel Demand Management (IBTDM) strategies in managing morning commutes with ridesharing. Separate time-varying incentive schemes for both rideshare drivers and passengers are proposed to maintain the user equilibrium. Since IBTDM strategies are usually non-mandatory, it is found that the optimal incentives vary with respect to market penetration. Subsequently, we took the difficulty of scheme implementation, system cost reduction, and net utility as the criteria, and obtained the optimal incentive schemes under different criteria. Finally, we verified the effectiveness of the above incentive scheme in promoting ridesharing and reducing system costs by means of experimental economics.