Convoy Applies ML for Predictive Crash Capability
June 25, 2020
Convoy introduced an application of machine learning and automation to qualify safe drivers. The new approach processes millions of records daily to better correlate the relationship between carrier safety events, such as speeding violations or vehicle maintenance, and related crash data. Already a pioneer in carrier safety standards, Convoy’s new technology identifies the safest carriers to allow into its network, yielding 16 percent fewer accidents than the industry average. Access to a safer carrier network increases on-time deliveries and cost savings for shippers, with lower claim rates and fewer cargo incidents. Commercial crashes are one of the major contributors to cargo loss, which is estimated to exceed $50 billion2 globally. Today, Convoy experiences a cargo claim less than once per 2,000 loads, whereas the industry experiences a cargo claim about once per 100 loads.
Historically, obtaining access to carrier safety data has been difficult
due to a lack of accurate tools and resources. The most widely used
information comes from the Federal Motor Carrier Safety Administration’s
(FMCSA) Carrier Safety and Accountability (CSA) program. The latter
generates overall ratings of Unsatisfactory, Conditional, or
Satisfactory for carriers; however, 95 percent of carriers have not
completed a full compliance review and remain ‘not rated’, limiting
visibility into the vast majority of safety records. This prevents an
adequate assessment of carrier safety during hiring and breeds
uncertainty and mistrust among shippers.