Investigating Taxi and Uber competition in New York City: Multi-agent modeling by reinforcement-learning

TL;DR

This paper uses multi-agent reinforcement learning models to analyze the competitive dynamics between traditional taxis and Uber in New York City, revealing patterns of market segmentation and impacts of regulations.

Contribution

It introduces a novel multi-agent reinforcement learning model to simulate driver behaviors and evaluate policy impacts on taxi and Uber competition.

Findings

E-hailers dominate low-density areas

E-hailers respond quickly to demand changes

Regulations indirectly affect market competition

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;