Investigating Taxi and Uber competition in New York City: Multi-agent
modeling by reinforcement-learning
- URL: http://arxiv.org/abs/2008.12530v1
- Date: Fri, 28 Aug 2020 08:08:18 GMT
- Title: Investigating Taxi and Uber competition in New York City: Multi-agent
modeling by reinforcement-learning
- Authors: Saeed Vasebi, Yeganeh M. Hayeri
- Abstract summary: This study investigates the existing competition between the mainstream hailing services (i.e., Yellow and Green Cabs) and e-hailing services (i.e., Uber) in New York City.
Data visualization techniques are employed to find existing and new patterns in travel behavior.
Results of our study illustrate that e-hailers dominate low-travel-density areas, and that e-hailers quickly identify and respond to change in travel demand.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The taxi business has been overly regulated for many decades. Regulations are
supposed to ensure safety and fairness within a controlled competitive
environment. By influencing both drivers and riders choices and behaviors,
emerging e-hailing services (e.g., Uber and Lyft) have been reshaping the
existing competition in the last few years. This study investigates the
existing competition between the mainstream hailing services (i.e., Yellow and
Green Cabs) and e-hailing services (i.e., Uber) in New York City. Their
competition is investigated in terms of market segmentation, emerging demands,
and regulations. Data visualization techniques are employed to find existing
and new patterns in travel behavior. For this study, we developed a multi-agent
model and applied reinforcement learning techniques to imitate drivers
behaviors. The model is verified by the patterns recognized in our data
visualization results. The model is then used to evaluate multiple new
regulations and competition scenarios. Results of our study illustrate that
e-hailers dominate low-travel-density areas (e.g., residential areas), and that
e-hailers quickly identify and respond to change in travel demand. This leads
to diminishing market size for hailers. Furthermore, our results confirm the
indirect impact of Green Cabs regulations on the existing competition. This
investigation, along with our proposed scenarios, can aid policymakers and
authorities in designing policies that could effectively address demand while
assuring a healthy competition for the hailing and e-haling sectors.
Keywords: taxi; Uber, policy; E-hailing; multi-agent simulation;
reinforcement learning;
Related papers
- Not Even Nice Work If You Can Get It; A Longitudinal Study of Uber's Algorithmic Pay and Pricing [20.694356269172857]
Ride-sharing platforms like Uber market themselves as enabling flexibility' for their workforce.<n>We describe our process of participatory action research with drivers and trade union organisers, culminating in a participatory audit of Uber's algorithmic pay and work allocation.<n>We find that after dynamic pricing, pay has decreased, Uber's cut has increased, job allocation and pay is less predictable, inequality between drivers is increased, and drivers spend more time waiting for jobs.
arXiv Detail & Related papers (2025-06-18T08:59:39Z) - GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching [82.19172267487998]
GARLIC: a framework of GPT-Augmented Reinforcement Learning with Intelligent Control for vehicle dispatching.
This paper introduces GARLIC: a framework of GPT-Augmented Reinforcement Learning with Intelligent Control for vehicle dispatching.
arXiv Detail & Related papers (2024-08-19T08:23:38Z) - Finding A Taxi with Illegal Driver Substitution Activity via Behavior Modelings [42.090136287906915]
Illegal Driver Substitution (IDS) activity for a taxi is a grave unlawful activity in the taxi industry.
Currently, the IDS activity is manually supervised by law enforcers.
We propose a computational method that helps law enforcers efficiently find the taxis which tend to have the IDS activity.
arXiv Detail & Related papers (2024-04-18T01:47:31Z) - Understanding human mobility patterns in Chicago: an analysis of taxi
data using clustering techniques [0.0]
Using the city of Chicago as a case study, we examine data from taxi rides in 2016 with the goal of understanding how neighborhoods are interconnected.
This analysis will provide a sense of which neighborhoods individuals are using taxis to travel between, suggesting regions to focus new public transit development efforts.
arXiv Detail & Related papers (2023-06-21T08:14:52Z) - Contingencies from Observations: Tractable Contingency Planning with
Learned Behavior Models [82.34305824719101]
Humans have a remarkable ability to make decisions by accurately reasoning about future events.
We develop a general-purpose contingency planner that is learned end-to-end using high-dimensional scene observations.
We show how this model can tractably learn contingencies from behavioral observations.
arXiv Detail & Related papers (2021-04-21T14:30:20Z) - Trading the System Efficiency for the Income Equality of Drivers in
Rideshare [23.53645438932742]
We study the income inequality among rideshare drivers due to discriminative cancellations from riders.
We propose an online bipartite-matching model where riders are assumed to arrive sequentially following a distribution known in advance.
arXiv Detail & Related papers (2020-12-12T16:04:06Z) - Emergent Road Rules In Multi-Agent Driving Environments [84.82583370858391]
We analyze what ingredients in driving environments cause the emergence of road rules.
We find that two crucial factors are noisy perception and agents' spatial density.
Our results add empirical support for the social road rules that countries worldwide have agreed on for safe, efficient driving.
arXiv Detail & Related papers (2020-11-21T09:43:50Z) - Urban Sensing based on Mobile Phone Data: Approaches, Applications and
Challenges [67.71975391801257]
Much concern in mobile data analysis is related to human beings and their behaviours.
This work aims to review the methods and techniques that have been implemented to discover knowledge from mobile phone data.
arXiv Detail & Related papers (2020-08-29T15:14:03Z) - Balancing Taxi Distribution in A City-Scale Dynamic Ridesharing Service:
A Hybrid Solution Based on Demand Learning [0.0]
We study the challenging problem of how to balance taxi distribution across a city in a dynamic ridesharing service.
We propose a hybrid solution involving a series of algorithms: the Correlated Pooling collects correlated rider requests, the Adjacency Ride-Matching based on Demand Learning assigns taxis to riders, and the Greedy Idle Movement aims to direct taxis without a current assignment to the areas with riders in need of service.
arXiv Detail & Related papers (2020-07-27T07:08:02Z) - Competing Bandits: The Perils of Exploration Under Competition [99.68537519404727]
We study the interplay between exploration and competition on online platforms.
We find that stark competition induces firms to commit to a "greedy" bandit algorithm that leads to low welfare.
We investigate two channels for weakening the competition: relaxing the rationality of users and giving one firm a first-mover advantage.
arXiv Detail & Related papers (2020-07-20T14:19:08Z) - K-Prototype Segmentation Analysis on Large-scale Ridesourcing Trip Data [0.0]
This study examines emerging patterns of mobility using recently released City algorithm of Chicago public ridesourcing data.
The goal is to investigate the systematic variations in patronage of ride-hailing.
Six ridesourcing prototypes are identified and discussed based on significant differences in relation to adverse weather conditions.
arXiv Detail & Related papers (2020-06-24T17:53:26Z) - Learning by Cheating [72.9701333689606]
We show that this challenging learning problem can be simplified by decomposing it into two stages.
We use the presented approach to train a vision-based autonomous driving system that substantially outperforms the state of the art.
Our approach achieves, for the first time, 100% success rate on all tasks in the original CARLA benchmark, sets a new record on the NoCrash benchmark, and reduces the frequency of infractions by an order of magnitude compared to the prior state of the art.
arXiv Detail & Related papers (2019-12-27T18:59:04Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.