Profitably underwriting commercial auto is a critical problem area for most insurers. The National Association of Insurance Commissioners reports that commercial auto losses have risen for the past four years, despite rate increases every quarter since 2011. Commercial auto rates rose an estimated 6 to 12 percent in 2019, according to the risk management firm Willis Towers Watson.
Commercial auto is challenged by some of the same trends that challenge the broader auto line of business:
- A growing economy that has put more vehicles on the road, bringing an increase in congestion, driver frustration, and crashes.
- Distracted drivers interacting with their phones and in-vehicle infotainment systems.
- Increase in repair costs as vehicle part have become more expensive.
- While drunk driving is down overall since 1980, driving while high is making up for the difference.
However, commercial auto underwriters also need to consider some these potential additional complexities:
- Inexperienced drivers behind the wheel, driven by a significant shortage of experienced commercial drivers and a high driver turnover.
- Varying nature of commercial cargo, e.g. risks associated with livestock are substantially different from those associated with hazardous chemicals or agricultural products with a short shelf life.
- Intrastate vs. Interstate transport of goods, including congestion along the routes traveled.
- Fleet maintenance and driver safety records have heightened importance for commercial auto.
Commercial auto underwriters conduct extensive research trying to determine these factors and other indicators in developing a potential customer’s risk profile and how well it aligns with the insurer’s risk appetite. But underwriters have been stymied by the range and complexity of the factors involved, as well as the volume and variety of data sources to be researched.
Data science and machine learning (ML) can transform this picture. By accessing and analyzing the vast amounts of third-party data, advanced decisioning platforms can make it substantially more efficient to make sound, data driven underwriting decisions. Decision platforms like d3 Underwriting, can unearth details that allows underwriters to rapidly prioritize submissions following carrier’s underwriting guidelines and risk appetite, unearth risk insights that would have been otherwise too difficult and time-consuming to track down manually, and highlight areas that may need further underwriting judgment.
By more accurately assessing the risks, solutions that leverage data science and ML can help insurers turn the corner on profitability for their commercial auto lines. I expect to see commercial auto loss ratios improve as more insurers start to take advantage of these data-driven approaches.
For further information about these trends, see: