A TomTom paper we recently came across on Carrier Management reminded us of a conversation we had with their team last year.
The paper explores how map and traffic data can add precision to auto insurance risk modeling.
While its examples lean toward personal auto, the underlying idea is equally relevant to commercial fleets: a driving signal without context rarely tells the full story.
A harsh braking event may indicate risky behavior, or a reasonable response to congestion, roadworks, or an incident ahead.
Speed has a different meaning depending on the posted limit, road type, traffic, weather, and time of day.
Context helps insurers understand not only what happened, but what it says about risk.
In commercial auto, context matters at scale. Fleets are rarely uniform: different vehicle types operate across different territories, routes, and working hours. Each of these and a dozen more factors shape the risk an underwriter is evaluating.
And even a detailed submission describes the fleet in isolation. It tells the insurer what is being insured, but not the conditions that shape the exposure.
A home base address and declared operating radius outline geographic exposure, but don’t factor in the roads, traffic patterns, weather, or time-of-day conditions the fleet actually encounters.
Combining fleet activity with its surrounding context places raw signals in their real-world setting. This supports more accurate risk selection and pricing, more targeted loss control, and better-informed claims decisions.
That was the focus of our webinar with TomTom, “Amplifying ROI in Commercial Auto Insurance: The Role of Contextual Data and Models.”
At Draivn, we bring together fleet telematics, video, contextual data, & actuarially validated frequency score, and turn these fragmented inputs into validated, insurance-ready risk exposure, natively integrated into insurance workflows.
If you joined us live, now is a good time for a refresher. If you missed it, you can catch up.
