Convoy Identifying Safer Carriers Through Machine Learning, Automation

Logistics provider Convoy, in an effort to use only the safest carriers in its network, has applied machine learning and automation to qualify safe drivers.

The new approach processes millions of records each day to compare the relationship between carrier safety events, such as speeding violations, and related crash data. Fleets identified as safe carriers by Convoy typically have 16% fewer accidents than the industry average, according to the company.

“Accidents are an unfortunate reality of the transportation industry,” said Lorin Seeks, director of carrier quality and compliance at Convoy. “This model predicts which carriers are likely to get into an accident, enabling us to select the best carriers and build a safer carrier group for our customers.”

Safer carriers can also increase on-time deliveries and reduce costs for shippers by lowering the number of claim rates and reduce incidents where the cargo is damaged. Convoy’s solution is able to predict a carrier’s likelihood of an accident by processing thousands of data points, such as carrier crash history, vehicle maintenance, and speeding and traffic violations, across millions of records. The machine learning model is then able to create scores for carriers in Convoy’s network, who are removed from the network if the carrier falls below safe thresholds.