How big data predicts and helps prevent train delays in Sweden

Public transport delays suck. There is nothing good about missing an important meeting because your train, bus, tram, or tuk tuk got delayed. So, in order to drive the highest levels of predictability for its users, Stockholmstag, the commuter train operator in Stockholm, has applied big data to its entire rail network in order to forecast disruptions in service.

The model, cunningly named “The Commuter Prognosis,” applies a prediction model to visualize the rail system as it will be two hours into the future. Using the predictions, Stockholmstag can forecast disruption in their service and, more importantly, their traffic control center can prevent the ripple effects that actually cause most delays.

According to Mikael Lindskog, communications director at Stockholmstag, the solution works like a seismograph. When a train is not on time the algorithm forecasts the risks of delay effects in the entire network by using historic data. Currently, the traffic control center analyzes any delays manually in order to prevent future delays. By automating the forecasting, they believe they can raise their service level significantly.

To understand how it works, imagine the algorithm forecasts that a train will be 10 minutes late to station C in two hours. To deal with this, the traffic control center issues a new train from station A that will arrive on time at station C. As soon as the new train has been put in motion the algorithm re-calculates and gives the traffic control center a new forecast for the entire train network within minutes.

The algorithm was developed by mathematician Wilhelm Landerholm. One assumes he’s previously been annoyed at train delays and wanted to “scratch his own itch.” With this solution, not only will operators be able to plan for delays, but they will also be able to inform passengers of risks of delays before they actually happen. On top of that, departure information will be more accurate so passengers can plan their trips better.

The algorithm and associated technologies can be adapted to be used for other sorts of public transportations in other cities in the future. It seems that Stockholmstag might just have found itself an entirely new revenue stream, all generated through the smart use of big data.