|
Abstract:
|
Ride-sharing platforms like Uber, Lyft, Didi Chuxing, and Ola are transforming urban mobility by connecting riders with drivers via the sharing economy. These platforms have achieved explosive growth, by dramatically improving the efficiency of rider-driver matching, and by calibrating the balance of supply and demand through pricing. For example, the dynamic adjustment of prices ensures a reliable service for riders, and incentivizes drivers to provide rides at peak times and location. Dynamic pricing is particularly important for ride-sharing platforms, because pricing too low for the market conditions creates the "wild goose chase" phenomenon: demand outstrips supply, and pickup ETAs get very long.
We review the approaches that have been proposed to solve these challenges, highlighting the statistical aspects. For example, dynamic pricing requires predictions of demand and supply over time and geolocation, which can be based on historical demand patterns, real-time information, and signals like events, weather, and points of interest. Matching algorithms require accurate predictions of driving time in the road network; such predictions are based in large part on geolocation information from vehicles in the road network.
|
