IBM researchers have redrawn bus routes of a major African city, using mobile phone call data
IBM researchers have conducted a ‘big data‘ exercise that allowed them to redesign bus routes in the African city of Abidjan, the largest city in the Ivory Coast.
The project is noteworthy because IBM redrew the bus routes for more efficiency by analysing mobile phone datasets of millions of people whilst they were on the move.
The thinking is that this type of data analysis will in future allow city and urban planners to better design infrastructure projects within cities.
The IBM project was carried out as part of the ‘Data for Development‘ competition, a research challenge sponsored by the mobile operator Orange. Normally, mobile operators tend not to allow outsiders to view their data, but in this case Orange gave IBM access to over 2.5 billion anonymous call records of five million mobile phone users in Abidjan.
According to the BBC, the anonymised data is the largest of its kind ever released.
It should be noted that the data provided was not the highly accurate GPS data (smartphone uptake in Africa tends to be more limited compared to conventional handsets), but rather the less accurate ‘call data’ that is captured when a mobile phone user connects to a nearby cell tower.
However, this call data did provide IBM researchers with enough information to allow them to redevelop optimised urban transportation routes in that city.
Like many African cities, Abidjan does not have a mass transit system. Instead, the population relies on approximately 539 large buses, as well as 5,000 minibuses and 11,000 shared taxis, in order to get around the city.
Despite this lack of structure, IBM researchers used analytics software on the datasets to determine that two additional bus routes needed to be added. It also recommended that an existing route should be extended.
“We found that we could reduce the travel times of people by 10 percent across the city,” Olivier Verscheure, senior scientist at IBM’s research laboratory in Dublin, said.
And Verscheure was keen to highlight the other potential uses of such large dataset analysis.
“If we could have merged the telco data with city data, such as the bus timetables we could have the potential to completely change the existing network,” he said. This would allow urban planners to more accurately plot where best to implement bike-sharing schemes, or electric vehicle charge points.
“Analysis of public transport and telco data would show how people move in a city and allow planners to create a bike sharing infrastructure from scratch, for example,” said Verscheure. “It is about understanding how people use a city, their movements and the digital signatures left by public transport to optimise the city’s infrastructure.”
The IBM project was presented to the Data for Development conference on 1 May, at Massachusetts Institute of Technology.
It neatly ties in with IBM’s ongoing campaign for smarter cities, and IBM is hoping to implement similar projects in other cities.
Are you a Big Blue Masterbrain? Try our IBM quiz!