By using new predictive analytics technology its developed in-house, the Canadian Automobile Association (CAA) says it will be able to send out a truck to a specific place before a breakdown occurs.

The Thornhill, Ont.-based firm developed the technology at its South Central Ontario office. Dubbed “Gen 2” the predictive technology is a proprietary machine-learning algorithm that uses historical data, weather and humidity indicators, and real-time traffic and GPS information.

The Gen 2 system was piloted in London, Ont. in January 2018, CAA says.

CAA’s CIO Kin Lee-Yow told IT World Canada that Gen 2 can predict the relative location, time and type of breakdown with 98 per cent accuracy and CAA is then able to place trucks within that certain geographic area to cut down on wait times.

During the summer months of 2018, rescue trucks reached CAA members in need of help an average of 11 minutes faster in the South Central Ontario region. CAA is optimistic the wait times will continue to improve.

In a June interview with IT World Canada, Lee-Yow described the technology as a progression of the Service Tracker mobile app that was also developed in-house. It’s an example of how the CAA is becoming more focused on its data as a key asset.

“[CAA] has taken almost 112 years of roadside assistance knowledge and by applying this technology and statistical algorithms basically allows us to have a better understanding of where we’re needed most,” Tony Tsai CAA’s assistant vice president of corporate communications told IT World Canada.

“It’s a change in the way we look at the business,” says Lee-Yow. “We’re looking at the data and at the purpose of what we’re trying to do.”

Right now CAA is working to fully implement Gen 2 across its South Central Ontario territory. It also has plans to expand to other CAA clubs and is currently helping to pilot it in other territories in Canada and the U.S., says Lee-Yow, stating that Winnipeg, Manitoba will likely start using Gen 2 by next year.

With files from Meagan Simpson