Disrputive taxi service provider Uber has seemingly found out a way to maximize its earnings by figuring out exactly how to position its drivers.

In a recent blog post, Uber data scientist Bradley Voytek talks about how Uber’s “science team” simulated a city and found out that taxi drivers can remain parked between trips and still earn twice as much as those who drive around in search of passengers.

Uber’s Data scientists created an artificial city called Uberg, that spans 100-by-100 blocks, existing in the artificial world of Python. Uber drops 250 passengers and 500 drivers in Uberg. Each passenger has a random destination in Uberg. Here drivers are simulated in three ways. Type-one drivers remain positioned between trips, while type-two drivers go back to the high-demand hotspots after each trip and type-three drivers motor around randomly between trips.

It was observed that when the dispatch distance is one block, which is equivalent to a street hail-only system, the drivers moving randomly lose less trips and get more customers but at a dispatch distance of five blocks when drivers receive passenger information in that perimeter, all the three types of drivers complete the same number of trips.
The simulation also teaches drivers to optimize shuttling between being stationary and being in a hotspot.

While Uber has been enlisting data scientists for sometime now, competitor Lyft is looking to boost its own operations through data analysis, given that it hired a vice president of data science from Netflix last December. With market competition rearing to build up and the inclusion of new tech Uber is looking to turn new stones with its research team.

Read more here.
(Image credit: David Holt)

Previous post

Fractal Analytics in Strategic Partnership with Loyalty Management giant, Aimia

Next post

National Express Calls Upon Qlikview To Help Process Data from Over 18 Million Journeys a Year