Linfox expands collection of driver data

Linfox asks its subcontractor truckies to sign agreements before they begin driving so the logistics giant can collect data on location and delivery times, in an expansion of its approach to big data.

Chief information officer Morgan Hurwitz today told the Connect Expo in Melbourne that its big data policy had, inadvertently, helped clear one of its drivers of wrongdoing following a recent accident.

“We had a recent example where we had a really unfortunate accident where, unfortunately, a gentleman died,” Hurwitz said.

“There was a coronial investigation and, because we have all these great data sources, the coroner took all this data and determined that the gentleman that had the accident – it was no fault of our driver – … drove head-on into the vehicle.

“We didn’t know we would ever use the data [that way]. We had it, and we could show the whole event and what was happening with the driver, where they were going, and how fast they were going, and how they were using the steering wheel.”

Linfox initially starting collecting data from sources like its fleet of trucks to improve driver safety and help avoid obstacles.

However, it is now expanding the approach after finding “the collection of data is really easy and really cheap”, Hurwitz said.

“I’m being educated about things like data lakes, and so the guys are building data lakes with multiple data sources that might be a data stream, it might be video, it might be weather data, it could be what’s happening with traffic,” he said.

Before a driver or subcontractor can begin working for Linfox, the company asks them to sign an agreement authorising the logistics giant to collect data from their vehicle.

“We have a couple of cases at the moment where – we use a lot of subcontractors to drive vehicles on our behalf – we’re asking them to provide some information around their location, because we have quite valuable goods on board and we also need to provide estimated delivery times to our customers,” Hurwitz said.

Hurwitz said most truck drivers had no issue with the company collecting the data. Those who were uncomfortable, he said, are reminded that they don't have to work for the company.

“A lot of people are really happy with it because they have less paperwork now. They can do it on their phone, and there’s really good uptake, but you’ll always get the exceptions that say ‘oh, we’re a bit concerned about privacy’," Hurwitz said.

“So the concession we have is: ‘You don’t have to do this. You don’t have to work for the company, it’s your choice, and you have a choice not to provide that information’."

Linfox began implementing a SAP HANA-based big data platform in 2013 as a proof-of-concept to give its control centres the ability to predict hazards and help drivers navigate around them.

Real-time truck positions are mapped geographically, while desk-based controllers in centres in Western Australia and Thailand can drill through the data to street level to work out why trucks might be delayed or over the speed limit in a particular location.

The platform also interrogates millions more historical data records to check if the same issues have occurred in that same area before, and maps the result.

Andrew Sadauskas attended the Connect Expo as a guest of Intel.