Sharing behavior in ride-hailing trips: A machine learning inference approach

Two-sided mobility platforms, such as Uber and Lyft, widely emerged in the urban mobility landscape. Distributed supply of individual drivers, matched with travellers via intermediate platform yields a new class of phenomena not present in urban mobility before. Such disruptive changes to transportation systems call for a simulation framework where researchers from various and across disciplines may introduce models aimed at representing the complex dynamics of platform-driven urban mobility. In this work, we present MaaSSim, a lightweight agent-based simulator reproducing the transport system used by two kinds of agents: (i) travellers, requesting to travel from their origin to destination at a given time, and (ii) drivers supplying their travel needs by offering them rides. An intermediate agent, the platform, matches demand with supply. Agents are individual decision-makers. Specifically, travellers may decide which mode they use or reject an incoming offer; drivers may opt-out from the system or reject incoming requests. All of the above behaviours are modelled through user-defined modules, allowing to represent agents’ taste variations (heterogeneity), their previous experiences (learning) and available information (system control). MaaSSim is a flexible open-source python library capable of realistically reproducing complex interactions between agents of a two-sided mobility platform. MaaSSim is available from a public repository, along with a set of tutorials and reproducible use-case scenarios, as demonstrated with a series of illustrative examples and a comprehensive case study.

show abstract

“…With such a setting, one can reproduce the impact of ride-pooling on system efficiency, revealed e.g. in Chicago [ 56 ].…”

Section: Resultsmentioning

confidence: 99%

Simulating two-sided mobility platforms with MaaSSim

Kucharski

Cats

2022

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…• Trip distance: This variable was proved to have high predictive power for the shared mobility usage (Taiebat et al, 2022); thus, it was selected as the context variable in the SP survey. The five levels of 3, 10, 15, 20, and 30 km were considered to cover different trip distances.…”

Section: Methodology Surveymentioning

confidence: 99%

Exploring the Role of Shared Mobility in Alleviating Private Car Dependence and On-Road Carbon Emissions in the Context of COVID-19

Zhang

Shao

Wang

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

Shared mobility is becoming increasingly popular worldwide, and travelers show more complex choice preferences during the post-pandemic era. This study explored the role of shared mobility in the context of coronavirus disease (COVID-19) by comparing the travel mode choice behavior with and without shared mobility. Considering the shared mobility services of ride-hailing, ride-sharing, car-sharing, and bike-sharing, the stated preference survey was designed, and the mixed logit model with panel data was applied. The results show that if shared mobility is absent, approximately 50% of motorized mobility users and 84.62% of bike-sharing adopters will switch to using private car and public transport, respectively. The perceived pandemic severity positively affects the usage of car-sharing and bike-sharing, while it negatively affects the ride-sharing usage. Under different pandemic severity levels, the average probabilities of private car choice with and without shared mobility are 38.70 and 57.77%, respectively; thus, shared mobility would alleviate the dependence on private car in post-pandemic future. It also helps to decrease the on-road carbon emissions when the pandemic severity is lower than 53. These findings suggest policymakers to maintain the shared mobility ridership and simultaneously contain the pandemic. Additionally, pricing discount and safety enhancement are more effective than reducing detour time to protect ride-sharing against COVID-19.

show abstract

“…We use these data on trip demand as an exogenous input into AgentX. The TNC Chicago data set has been extensively used in transportation research − since its public release. Chicago is also one of the largest ridesourcing markets in the U.S. with ridesourcing making up about 3% of the total regional VDT .…”

Section: Datamentioning

confidence: 99%

Life Cycle Air Pollution, Greenhouse Gas, and Traffic Externality Benefits and Costs of Electrifying Uber and Lyft

Mohan

Bruchon

Michalek

et al. 2023

Environ. Sci. Technol.

View full text Add to dashboard Cite

Transportation network companies (TNCs), such as Uber and Lyft, have pledged to fully electrify their ridesourcing vehicle fleets by 2030 in the United States. In this paper, we introduce AgentX, a novel agent-based model built in Julia for simulating ridesourcing services with high geospatial and temporal resolution. We then instantiate this model to estimate the life cycle air pollution, greenhouse gas, and traffic externality benefits and costs of serving rides based on Chicago TNC trip data from 2019 to 2022 with fully electric vehicles. We estimate that electrification reduces life cycle greenhouse gas emissions by 40−45% (9−10¢ per trip) but increases life cycle externalities from criteria air pollutants by 6−11% (1−2¢ per trip) on average across our simulations, which represent demand patterns on weekdays and weekends across seasons during prepandemic, pandemic, and post-vaccination periods. A novel finding of our work, enabled by our high resolution simulation, is that electrification may increase deadheading for TNCs due to additional travel to and from charging stations. This extra vehicle travel increases estimated congestion, crash risk, and noise externalities by 2−3% (2−3¢ per trip). Overall, electrification reduces net external costs to society by 3−11% (5−24¢ per trip), depending on the assumed social cost of carbon.

show abstract

Sharing behavior in ride-hailing trips: A machine learning inference approach

Cited by 25 publications

References 41 publications

Simulating two-sided mobility platforms with MaaSSim

Simulating two-sided mobility platforms with MaaSSim

Exploring the Role of Shared Mobility in Alleviating Private Car Dependence and On-Road Carbon Emissions in the Context of COVID-19

Life Cycle Air Pollution, Greenhouse Gas, and Traffic Externality Benefits and Costs of Electrifying Uber and Lyft

Contact Info

Product

Resources

About