All aboard: big data driving public transport improvement
We talk a lot about big data, M2M and their applications making cities smart, but for a real life glimpse at how these technologies can work together, take a look at Transport for London (TfL).
TfL uses big data analysis to help manage and optimize its infrastructure as it handles transportation for a city of 8.6 million people. The service gathers information from multiple sources, vehicle-mounted sensors, traffic signal sensors, surveys, focus groups and social media to help it understand customer needs.
The organization also collects M2M payment data – passengers must use either a contactless credit card or one of TfL’s own contactless Oyster cards to pay for travel.
The insights available from these data stacks are constantly improving, for example, US researchers are developing systems that enable existing traffic sensors to distinguish bicycles from other vehicles.
The UK Highways Agency (HA) uses road sensors to collect data on traffic flows and GPS data to estimate journey time, making this information available to third parties.
London commuters frequently use more than one method of transport, but their journey can now be understood thanks to use of contactless technology. The big snag is that the system can’t tell when travellers step off the bus, and this is where big data steps in.
Speaking with Forbes Lauren Sager-Weinstein, head of analytics at TfL explains: “We asked, ‘Can we use big data to infer where someone exited?’ We know where the bus is, because we have location data and we have Oyster data for entry.
“What we do next is look at where the next tap is. If we see the next tap follows shortly after and is at the entry to a tube station, we know we are dealing with one long journey using bus and tube.”
Insights like these give transit management a good insight into bus crowding and demands made on facilities and infrastructure at different waypoints across London.
Systems don’t always run smoothly, and TfL has found this data incredibly useful when it comes to crisis management. The organization has used data visualization to map passenger journeys during both scheduled (e.g. sporting events), and unscheduled (e.g. temporary station closures) service changes.
For example, when a bridge used by 870,000 people each day was closed to vehicle traffic, TfL was able to use data analysis to help guide its response.
The data showed that around half of the journeys across the bridge began or ended close to either side of the bridge, so travelers could still walk across the bridge. Sager-Weinstein explained that those who were not making a local trip were then given increased bus services on alternative routes and personalized messages to explain the likely impact on their journey. “It was very helpful that we were able to use Big Data to quantify them,” he said.
In future the company hopes to improve its data analysis systems to deliver more real time insights and to gather insights from a wider range of data sources. TfL uses this data to help inform via social media and also provides its data to third party developers through an API.
Beyond TfL the UK Government’s DfT and its agencies have published 255 datasets so far in an attempt to nurture big data analysis in public transport.
Regular readers will know this work isn’t just taking place in the UK. Public transit operators across the US, Australia and beyond are also integrating big data into their systems as they struggle to efficiently manage infrastructure (and meet environmental targets) while also addressing the needs of growing urban populations.
Read more about big data and public transport here and take a look at how Orange Business Services can help transform your data into business insights here.