01698025

Component

Ride-hailing companies such as Uber and Lyft represent a popular and growing mode of transit in cites worldwide. These companies employ surge pricing in real time to balance the needs of both drivers and riders. Surge prices in the next few minutes to hours could be predicted to encapsulate the complex evolution of service fleets and service demand in the short term. Surge pricing, if effectively predicted and disseminated to both drivers and riders, can be used to more efficiently allocate vehicles, save users money and time, and provide profitable insight to drivers, which ultimately helps the optimality and reliability of transportation networks. This paper explores the spatio-temporal correlations among the urban environment, traffic flow characteristics and surge multipliers. The authors propose a general framework for predicting the short-term evolution of surge multipliers in real-time using a linear model with L1 regularization, coupled with pattern clustering. This model is able to predict Uber surge multipliers in the urban areas of Pittsburgh up to two hours in advance using data from the previous hour within 3-5% error, out-performing the overall mean and the historical average. Cross-correlation of Uber and Lyft surge multiplier is also explored.

This paper was sponsored by TRB committee AP020 Standing Committee on Emerging and Innovative Public Transport and Technologies.

19-04871

English

6p

2019

Transportation Research Board 98th Annual Meeting

Digital/other

Figures; Maps; References (4)

Congestion pricing; Paratransit services; Peak hour traffic; Real time information; Traffic flow; Travel demand management; Urban highways

Uber

Pittsburgh (Pennsylvania)

Finance; Operations and Traffic Management; Passenger Transportation

Transportation Research Board Annual Meeting 2019 Paper #19-04871

TRIS, TRB, ATRI

Dec 7 2018 9:44AM