Uber, the giant logistics company has today announced that they teamed up with a number of institutions to host a machine learning hackathon in Kenya.
The company partnered with Zindi, Flare and the World Bank to host this event that aims to reduce the mortality rate of road accidents by developing solutions that will lead to quicker response times for ambulances.
Here was the challenge: The World Bank has collected information on thousands of traffic accidents that occurred in Kenya in 2018 and 2019. Zindi provided a platform for the participants to use training data (recorded crashes upto June 2019 and data from Uber Movement, road survey data and weather patterns to identify patterns of risk across the city. They needed to use these findings to place six virtual ambulances around the city moving them around throughout the day with a goal of minimizing distance travelled when responding.
Darius Moruri won first place in the Uber hackathon and his proposal had an approach that combines custom functions to re-project the city’s geographic coordinate system as well as finding optimal locations across Nairobi where ambulances can be positioned.
Other solutions developed from the hackathon event include one that was reliant on using data on common crash locations in Nairobi to determine the best locations to avail services. The teams used traffic data from Uber Movement.
Brian Njao, Head of Uber in East Africa said, “Bringing together young data scientists, startups and innovators in Kenya with the goal of providing effective solutions to assist those in need is at the heart of this challenge. We are so excited to witness the various strategies and solutions that can one day be used to save the lives of many Kenyans.”
