Tag Archives: auto insurance

Personal lines coverage evolves with exposure data tracking

Increasingly, individuals are having their driving habits and living environments monitored electronically. A recent Insurance Journal article cited Milliman’s Sheri Scott discussing how exposure data tracking is shaping new underwriting practices for personal lines coverage like auto insurance.

Here’s an excerpt from the article:

Exposure tracking and the advent of autonomous vehicles are shifting personal auto insurance risk exposure from dependence on driver skills, estimated distances driven and garage location to the precise determination of vehicle locations, driving habits, driving distances and traffic conditions, all determined through the collection of trip data gathered in real time.

Yet even these underwriting considerations will soon be supplemented, if not supplanted, by the loss experience of automated vehicles and their manufacturers.

This transformation will not be without risks of its own, Scott said. In particular, she cited disruption of networked communications as a hazard, especially as vehicle occupants become dependent on automated control and less practiced at taking control of a vehicle.

“If some kind of communication goes down, there could be a very serious occurrence,” she said.

Pooling autonomous vehicle risk

The production of autonomous vehicles is shifting the responsibility of automobile-related insurance risk. Some manufacturers have already stated that they would assume liability for accidents caused by faulty technology in their cars. However, autonomous carmakers would likely spread that liability out among the suppliers of the cars’ software, systems, and devices.

According to Milliman’s Chris Kogut, a Supplier Product Liability Autonomous Share (SPLASh) insurance pool may help manufacturers and suppliers effectively manage the risk associated with autonomous car accidents.

Continue reading

Telematics and machine learning can help insurers employ usage-based insurance

Telematics can help auto insurers implement usage-based insurance (UBI) by obtaining valuable data related to individuals’ driving behaviors. However, producing actionable information through generalized linear model (GLM) methods has been difficult for auto insurers. Machine learning techniques provide insurers with a better way of analyzing big data.

Milliman consultants Marcus Looft, Scott Kurban, and Terry Wade provide perspective in their article “Usage-based insurance: Big data, machine learning, and putting telematics to work.”

For auto insurers, machine learning holds the promise of enabling carriers to explore hundreds, if not thousands, of factors involved in calculating the potential risk of individual customers. Moving beyond GLM and introducing machine learning techniques with telematics data may enable insurers to leverage key competitive advantages.

UBI pricing necessarily supersedes traditional GLM methods because the complex interactions of the factors in play require machine learning to uncover them within a reasonable timeframe in order to be cost-effective. Pricing differences often cannot be fitted by GLM distributions. And correlations between telematics and non-telematics effects will tend to disturb the clarity of results in a single GLM. Distribution over different frequency and severity models only confuses the analysis of differences within telematics policies.

GLM techniques will thus always show how a business differs in terms of its dependencies on a limited set of specific factors, such as age, or how much mileage goes on a car, or other very high-level factors. But if a whole model is taken and everything modeled together to try to understand the risk for all of the policies, in the end there tends to be only a mixed bag of different effects. An insurer still hasn’t been able to look very deep into its business.

Ride sharing is opening up new business opportunities for auto insurers

Transportation network companies (TNCs), better known as ride-sharing services, such as Uber, Lyft, and Sidecar, have created challenges for regulators and insurance companies. However, as cities and states work on governing this new mode of transportation, insurers should take advantage of the opportunity to develop new products covering ride-sharing drivers.

In their article “Ride sharing and insurance issues,” Milliman consultants Michael Henk and Peggy Brinkmann discuss the risks of insuring TNC drivers as well as the new opportunities for innovation. Here is an excerpt:

One of the central ambiguities in ride sharing is the question of who pays when there is an accident… To answer the coverage question, it is helpful to break down the vehicle use into four different categories:

1) Ride sharing driver isn’t logged in to the ride sharing service and is thus not available for hire.

2) Ride sharing driver is logged in to the ride sharing service and is available for hire, but has not yet found a passenger.

3) Driver and passenger have confirmed a ride share and the driver is en route for pickup.

4) Ride share is in progress.

There is general agreement that accidents arising in the first category would be covered by the personal auto policy, but the second category has been more controversial…

Even insurers that are denying claims related to ride sharing are concerned about covering the personal usage of vehicles also used for ride sharing…

Without access to standard personal auto coverage, though, ride-share drivers are in need of new products and/or rating plans. Today’s typical rating plan varies rates by pleasure, work, and business usage, and mileage is difficult to capture accurately. To address concerns that the ride-share vehicle personal usage risk might be higher than expected under current rating plans, carriers could introduce a new variation of business usage for ride-sharing vehicles. Carriers could also perhaps require ride-sharing vehicles to enroll in usage-based rating programs in order to ensure the most accurate data about vehicle usage to get appropriate rates for the personal use of these vehicles.

Driving for profit: A view of the UK private and commercial motor insurance markets 2013

In this year’s edition of Driving for Profit Milliman consultants Derek Newton, Gary Wells, and Vincent Roberts present the results of our analyses of the performance of the private and commercial motor market in the UK.

Starting with UK Private Motor, the overall performance of the market in 2013 has resulted in a pretax net insurance ratio of 3.4%. This ratio has been highly distorted by the large prior years’ reserve release made by the Direct Line Group. Overall performance (including reserve releases from prior years) of the UK Commercial Motor market has deteriorated in 2013 to a pretax net insurance ratio of -6.9% (from -5.7% in 2012), following an improvement in performance from its trough in 2009. The causes of the deterioration in 2013 were twofold: deterioration in the operating loss for current year business; and strengthening of prior years’ reserves.

This Milliman Market View reviews some of the statistics behind the recent performance of the UK Private and Commercial Motor insurance markets. In particular, we consider market profitability, premium rates, claim frequency and average size, and comparative performance of major players in the markets.

How can text mining affect underwriting practices for auto insurance?

Phil Borba recently discussed his latest text-mining analysis that links drug-impaired driving to higher claim severity with Carrier Management. In this article, he explains how text mining can reveal valuable information hidden in the narratives of auto insurance claims adjusters that could lead to improved underwriting practices.

Here is an excerpt:

These tidbits of textual information about drug-impaired driving don’t just inform the claims-handling process, but they can also provide valuable input to underwriters, Borba says.

Finding that an individual has been under the influence of a drug or taking medications could provide a reason for a non-renewal, he says. “Or it can become a rating variable—almost similar to if you had been convicted of a DWI [driving while intoxicated]. You are then put under a different category,” Borba says, suggesting underwriting and pricing applications.

A report summarizing Milliman’s findings about DUID—driving under the influence of a drug—was published in the April edition of Milliman’s Insight publication. The report notes that other carrier benefits of identifying drug-impaired driving include better claims triage and assignment of liability.

“Finding that the other driver was DUID may be cause for a subrogation recovery against that driver, or provide enough additional evidence to increase the likelihood or size of recovery,” the report notes.

Explaining the claims triage benefit, Borba says that if carriers react quickly to any indication of drug use, then they will be able to reroute claims to adjusters who are familiar with different medications and know how to test for those. That’s important because the establishing that someone was DUID is a complex process, he says—much more involved than establishing a DWI.

Previously, Phil identified major considerations concerning the use of cell phones on claim adjusting and auto insurance premiums in his paper “Distracted driving: Text-mining accident descriptions.”