eduzhai > Applied Sciences > Engineering >

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

  • king
  • (0) Download
  • 20210507
  • Save

... pages left unread,continue reading

Document pages: 12 pages

Abstract: The taxi business has been overly regulated for many decades. Regulations aresupposed to ensure safety and fairness within a controlled competitiveenvironment. By influencing both drivers and riders choices and behaviors,emerging e-hailing services (e.g., Uber and Lyft) have been reshaping theexisting competition in the last few years. This study investigates theexisting competition between the mainstream hailing services (i.e., Yellow andGreen Cabs) and e-hailing services (i.e., Uber) in New York City. Theircompetition is investigated in terms of market segmentation, emerging demands,and regulations. Data visualization techniques are employed to find existingand new patterns in travel behavior. For this study, we developed a multi-agentmodel and applied reinforcement learning techniques to imitate driversbehaviors. The model is verified by the patterns recognized in our datavisualization results. The model is then used to evaluate multiple newregulations and competition scenarios. Results of our study illustrate thate-hailers dominate low-travel-density areas (e.g., residential areas), and thate-hailers quickly identify and respond to change in travel demand. This leadsto diminishing market size for hailers. Furthermore, our results confirm theindirect impact of Green Cabs regulations on the existing competition. Thisinvestigation, along with our proposed scenarios, can aid policymakers andauthorities in designing policies that could effectively address demand whileassuring a healthy competition for the hailing and e-haling sectors.Keywords: taxi; Uber, policy; E-hailing; multi-agent simulation;reinforcement learning;

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×