Our Blog

What You Need to Know About Driver Scoring

What You Need to Know about Driver Scoring/Why You Should Care

From a fleet safety perspective, you are making decisions based on scores, right?You are providing feedback to drivers based on this score. As an insurer, you may be predicting and pricing exposure to risk with these scores. You would also hope that your insured’s use of a loss prevention program actually delivers the desired end result, namely, an improvement in loss history. You may even financially participate in your insured’s use of this technology if it aids your underwriting and fleet loss histories. These driver scores ought to be as accurate as possible, right?And yet there is a pervasive lack of sophistication when it comes to driver scoring. Lots of “good enough” or “better than nothing” scoring, but very few cases yielding truly accurate driver scoring.
This paper explains how you can evaluate the scoring; specifically why typical driver scorecards are flawed; and also provides a guide to clarify what questions you ought to be asking your vendor to determine if scores are as accurate as possible. You simply can’t draw good scoring conclusions from seriously flawed science.

Driver Scoring is Focused on Interpreting the Risk of Vehicle Momentum Changes

There is a tremendous range of sophistication in the calculation of driver scorecards from telematics data. Driver scoring is predominantly driven by the interpretation of changes in vehicle momentum as measured most typically by accelerometer data. Most currently available solutions fall far short in applying the best science to the scores. The end result of this is data that is seriously compromised in its determination of risky driving behaviors and events. Each potential compensation, poorly applied (or not applied at all), will lessen the accuracy of your scores.

What is Wrong with G-Forces?

While g-force (or Delta V, Delta T) evaluations are the key to driving risk identification, a g-force, by itself, is a poor indicator of risk. G-Forces do effectively measure momentum changes, but those momentum changes only have real meaning when taken into the context of the entire driving situation. You don’t really know if you have a real event by looking just at the g-force. You have no idea of the magnitude of the event from a g-force reading. A high g-force may actually represent relatively low risk, and visa versa. A focus on g-forces is a vestigial remains of the days when driver scoring was new and data transfer was much more expensive.

What is Wrong With the Typical Solution?

The typical solution, out of expediency, will measure exception-based events. The device in the vehicle captures “events” that exceed pre-determined and arbitrary thresholds. This means something along the lines of “I exceeded a pre-determined g-force and this therefore qualifies as a hard-braking (for example) event”. The tally of the number of such infractions thus goes into the calculation of some overall driving score. While being better than nothing, this approach is only a very crude proxy for the determination of driving risk. While it may have some limited value to fleets (it is better than nothing), the commercial insurer is looking for greater, more accurate identification of driving risk. With an “event-based” system (real time determination at the device level), this accuracy is impossible to attain. A sophisticated scoring system should take advantage of the opportunity to draw conclusions from much bigger data sets. Bigger data post-processed yields the greatest insight into behaviors since all appropriate compensations can then be applied in parallel.

How Does Poor Science Negatively Impact Driver Scoring?

  • Are your driver scores a function of the challenge of the driven route? A more challenging route has the opportunity for more driving infractions, thus worse driver scores. Good science, looking at second by second momentum changes and actual driving events, can determine the impact that the route has on driver scores. Drivers should not be punished for driving well in more challenging environments yet insurers want to know their total exposure to risk (which includes the impact of the route).
  • Do your driver scores fail to differentiate between the magnitude of different events? “I know Joe had a hard-braking event last week but did it just exceed a pre-determined g-force threshold or was it a slam on the brakes precursor to an accident?” How do you differentiate this event from any other braking event? Both the frequency and severity of driving events should be taken into consideration.
  • Do small vehicles score worse than larger vehicles? Without appropriate compensation they do. You cannot effectively score driving behavior without the weight of the vehicle taken into the calculation. Larger vehicles score better because they can’t make the momentum changes that smaller vehicles are capable of. Driver scoring is a function of vehicle momentum change analysis.
  • Can you change behavior and notice the difference in your score (immediately)? Is scoring sophisticated enough to immediately “react” to changed behavior?
  • Can you accurately compare all drivers so you can determine which ones are targets for improvement? Are you accurately segmenting where risk actually lies across your entire driver base?
  • Is there a “back end” to your solution? Meaning, once you have your score, do you know how to interpret it, provide appropriate intervention/feedback to drivers, and track resultant changes in behavior
  • Can you measure the underlying behavior tendencies that yield exposure to eventual actual driving events? (Second by second analysis of all “accelerometer noise” in addition to identification of events
  • Is an “event” determined by more than just one variable exceeding a pre-determined threshold? To really understand an event, you should include consideration of speed at time of g-force infraction, weight of vehicle, duration of event, known risk of combination of behaviors, severity of event, impact of the driven route on event determination, etc.
  • The simplest question can be the most meaningful. Ask your potential vendor “How is a risky driving event determined?”


Science, applied correctly, can provide very meaningful identification of risky driving behavior and be the basis for an effective driver improvement program as well as be the basis for delivering more insight in regards to underwriting. While UBI solutions have been mainstream for a long time, required accuracy of driver scoring has been a gating factor in generating driver scores that can truly give commercial insurers superior insight into the risk exposure of driving behavior. The pending expansion in telematics data interpretation in the commercial marketplace will be based on delivering more accurate driver risk scoring. The “good enough” scoring of so many driver dashboards and the simpler focus on UBI scoring simply will not get the job done in the commercial arena.

Accuscore Introduces Driver/Road Risk Scoring for Insurers and Fleets

Building on an existing score that combines driver behavior and road characteristics, the new scoring function provides separated views of risk tailored to the respective needs of insurers and fleets.

Accuscore, a San Diego-based driver scoring system provider formerly known as Acculitx, has introduced a separated scoring function for insurers and fleets. While the fleet sees scoring that more purely reflects the drivers’ behavior, the insurer receives scoring that adds in the risk elements of the driven road for a more complete view of overall risk exposure, according to Accuscore.

Alan Mann, President, Accuscore.

The vendor explains that scoring can reflect not only factors that the driver controls, but also uncontrollable factors such as the nature of the driven route.  If risk is associated with changes in momentum, it is natural that the driver on a route with relatively more stopping, starting, and turning, will have the opportunity to have more negative driving events and; therefore, a worse score. Separated scoring is required to be able to utilize this type of insight as both an effective loss prevention tool for the fleet and a tool of significant underwriting insight to the commercial insurer.

The new Accuscore scoring capability builds on an existing score that combines driver behavior and road characteristics. While the commercial insurer would like to fully understand the risk of the total driving experience, including the driver’s behavior as well as the risk associated with the road, the fleet manager/safety manager wants good driving behavior to be reflected with a good score even on a more challenging road, the vendor explains.

“We want the fleet drivers to get a score that purely represents their driving behavior without being penalized by the nature of the driven road,” elaborates Alan Mann, President, Accuscore. “On the other hand, the insurer wants a more complete picture of risk exposure which includes both the driver’s behavior and the nature of the road being driven on.  Accuscore scoring is uniquely positioned to provide this insight as every second of performance quantifies subtle motion changes as well as identifying specific incidents of highest risk.”

Second-by-Second Motion Analysis

Accuscore describes its scoring system as providing in-depth, second by second motion analysis, with multiple compensations applied to each second, which achieves the sensitivity of scoring that allows the vendor to isolate the “pure driving” score from the effects of varying road characteristics.

“The actionable nature of driver risk scoring is associated with its value as a loss prevention tool as well as an indicator of risk exposure for underwriting purposes,” continues Mann. “The fleet and the insurer have different needs in terms of scoring insight to fully monetize the value of driver scoring.”

Article orginally posted on: https://iireporter.com/accuscore-introduces-driverroad-risk-scoring-for-insurers-and-fleets/

The Ideal Smart Phone App for Fleets

Imagine if commercial fleets were able to deploy a sophisticated driver behavior scoring solution without the cost barriers of buying and installing costly devices in the vehicle to capture that information.

Now imagine if these fleets were able to understand not only who their poor drivers are, but also who their best drivers are as well, with a simple score. And thereby being able to implement programs to assist the needed drivers and recognize and reward the optimal drivers.

Now also imagine being able to focus on improving driver performance in an effort to continually improve safety, reduce risk, and therefore reduce costs associated with accidents.

And finally, imagine being able to do it all from the driver’s Smart Phone and do it with superior accuracy. 

Mobile App Reduces Telematics Barriers

Fleet managers already know driver safety equates to vehicle efficiency and driver productivity. Today, most well-implemented, proactive fleet safety programs are employed via a telematics device-based solution.  Unfortunately, this traditional model is far from perfect. These systems require the production and distribution of a physical device, resulting in higher startup and hardware costs. This variety can be expensive for fleets to maintain, driving down the potential profits reaped from such a program. In addition to the cost of the OBD device, there are costs involved with transmitting and translating the data into meaningful intelligence. Now using superior technology applied to data collection via smartphones, the perfect tool to manage and understand your drivers and how they affect the wear and tear on your vehicles, and how each driver contributes to the overall accident risk for your fleet, is here. Unlike OBD device systems, smartphones or mobile telematics solutions are equipped to gather driving intelligence seamlessly without the need for driver interaction or additional equipment.

Today in U.S. only 30% of fleets have deployed telematics devices in their vehicles. Those devices are predominately installed in larger fleets. Most of the smaller fleets of 50 or less vehicles do not utilize telematics. A driver behavior scoring system must be very easy to deploy, manage and come at a very reasonable price point to achieve any adoption. The monthly cost will either be absorbed by the insurance company or by the fleet if there are value added telematics services associated with the application. Using the smartphone for collecting data removes the burden of device inventory management and replacement due to wear and tear. Safer drivers are more efficient and productive drivers.



With smart phones reducing telematics cost barriers, mobile telematics gives fleet managers insights at an affordable price making a powerful shift in the ability to implement a well-run vehicle telematics program for fleets of all sizes. As a fleet manager looking for a resource for ensuring safety, the ideal smart phone app would provide these following elements:

  • Understand how the vehicles are drivenInsight to where the vehicles are driven; when they are driven; and how much wear and tear are they incurring. Overall benefits to fleets of safer driving—repair costs, community reputation, insurance cost, loss of use of vehicles/employees, workman’s comp claims from accidents, improvements in fuel efficiency, tire wear, brakes, etc.
  • Understand which drivers are at a higher risk of getting into an accidentEvery driver in the fleet would be scored accurately. The score would be broken down into multiple levels and then summarized as aggression, distraction and total score. A driver’s Aggression Score is an indicator of at-will behavior. A poor aggression score generally leads to significant wear and tear on the vehicle and higher gas consumption while also being correlated with driving risk, while a poor Distraction Score indicates a higher propensity of getting into an at fault accident.  The distraction score indicates a propensity to need to aggressively correct the vehicle’s position/momentum based on the driving situation.
  • Improve everybody in the fleetBy knowing the performance of every single driver and providing feedback for every single driver, the system will improve all drivers, even the best drivers, and achieve a safer fleet across the board. The ideal solution is not just looking for the worst drivers with the worst driving events, but scoring and ranking all drivers. With a properly managed system, and the ability to provide feedback for all drivers, the entire fleet will improve.
  • A CLEAR DEFINITION OF THE DESIRED LEVEL OF SAFETY – To create movement towards a desired level of safety, the ideal smart phone app would provide a simple strategy to set goals and measure where you’re at.
  • All Employees are Actively engaged in safety initiatives – Mobile telematics allows every employee to be actively engaged in safety, producing tangible results.
  • a Standardized driver score normalizedand weighted – All drivers, despite differences in driving responsibilities, types of vehicle, speeds driven, etc., must ultimately yield a standardized and comparable score. Just like you can trust a credit score of 750 to mean the same thing to different mortgage lenders, the ideal app world could use that same concept of uniformity to rank drivers and assess risk exposure based on a uniform scoring system.
  • Negotiate a better insurance rateBy having defendable numbers and the improvement over time, the fleet may be able to take these numbers to their insurance carrier and negotiate a better rate. For the self insured, financial benefits of accident loss improvements accrue directly to the bottom line. 

Targeted Coaching

Once these elements are known, the fleet is able to actively manage and improve the driver behavior and hence improve the safety of their entire fleet. This can be achieved through driver specific coaching right on the smart phone that addresses the exact deficiencies that a particular driver has. Because the ideal system would have such detailed knowledge, the system can generate recommended coaching elements in a targeted manner that applies to a particular driver, and not wasting time with coaching material that is not relevant. With the ability to know which drivers need improvement, and corrective training, a very simple reward-based system for good and improved driving can be implemented.

Staying Ahead Of Safety

Fleet safety begins with safety managers and fleet owners recognizing the tremendous impact that vehicle accidents have on workplace safety, their reputation and their bottom line. A mobile telematics solution should provide all drivers with effective feedback and coaching, allowing employers to take the necessary steps to retain good drivers. Creating positive incentives motivates even the best of drivers. Even drivers with impeccable records need feedback and coaching on an ongoing basis. The ability to recognize and reward good behavior will motivate continued safety performance.


The World Should Get Ready for a FICO-type Score of Driving

Creating a Uniform Standard of Scoring Similar to a FICO Score for Driving Behavior and Risk Assessment

Just like your credit score is an institution, and is generally accepted as a tool for underwriting financial risk, there will soon be a generally accepted FICO-type score for driving. What are the signs that the world is ready for a FICO-like score of driving?

Similar to how a good credit score can help you obtain a loan at a favorable rate, what if a good driving FICO-like score helped you obtain better insurance rates or made you more desirable to potential employers? FICO, or Fair Isaac Corp., is the industry leader in credit scoring. Its credit score – the FICO Score – is used by more than 90% of lenders. Insurers and drivers should get ready for the next logical step in auto insurance… a FICO-like score of driving to assess risk and help them obtain better insurance rates.


In the past, automotive and fleet insurers have been relying on past loss histories to determine risk and renewal strategies. When it comes to standardization of driver behavior and related risk assessment, there is none. To date, even the Usage-based Insurance (UBI) programs currently in operation have no defined and uniform standards in the way insurance companies assess driver behavior, other than miles driven. Ironically, the actuaries who evaluate risk by using statistical data are using only proxies of risk exposure that represent only directional representations of actual driver behavior. In the credit world, FICO is essentially used to determine “the likelihood that you will pay all of your obligations (debt) on time for the foreseeable future.” A FICO-like score for driving would essentially be determining “the likelihood that you will be involved in an at-fault accident sometime in the foreseeable future.”

Think about this for a minute. A leading factor in pricing vehicle insurance being used by actuaries today is ‘how many miles you drive annually.’ With that in mind, think about your credit score. It is not based on ‘how much money did you spend.’ Your credit score factors in payment history, amounts owed, length of credit history, types of credit and new credit. In essence, FICO is interpreting your behaviors around money management and the likelihood you will make a payment. Better behavior reaps better rewards.

What if there was a way to truly assess a driver’s likelihood to avoid situations that result in a collision, in addition to those miles driven? Imagine being able to switch from one insurance company to another and being able to provide a specific driver score that is meaningful across all insurance platforms. Imagine as well a level of transparency that allows a driver to see the factors, or choices they have made, that affect the driving score. So why aren’t actuaries for vehicle insurance following this model?

The answer lies in innovation and the fact that the risk of an at-fault collision depends on more than just choices that the individual driver makes. We share the road and the risk with millions of other drivers. There has never been enough computing power, until very recently, that could consume the quantity of behavioral information around driving and the driven environment that could be applied across all platforms.

Insurance companies require this type of standardized information for peer comparison and predictive modeling to forecast future outcomes and results. But, because there has been no uniformity in this area, and because actuaries typically require five years of historical data, it has been hard for insurers to keep pace with technological advancements and the volume scale of the data. So why is a uniform standard driving score important? Because it puts every driver on a level playing field when assessing their risk.



A standardized driver scoring system would be comprised of both actual driving behavior and contextual elements. Behaviors like aggressive driving are a choice a driver makes while distracted driving results in reactions the driver must make to correct a position of risk in traffic. Drivers and fleets would pay insurance rates that reflect their actual driving behaviors. These driving choices are not made in a vacuum, though. To fully understand risk requires a contextual view and data on the driven environment – road service, accident history, time of day, local weather, traffic, congestion and many other circumstantial variables.

Determining a driver or fleet’s underlying risk based on unprecedented visibility into fleet and individual driving data provides better data for better decisions. Understanding a driver’s behavior along with the impact of the driven environment will give insurers the ability to apply rating models to verified driving and vehicle data that they have never had before. It will also create an environment where insurance companies can quote based on the actual safety results of both driver and vehicle in a more timely fashion and reduce time to market. Over time it will also allow insurance companies to reward consumers who invest in active safety systems such as lane departure warning and automatic braking.

For the commercial fleet side, there are many different telematics service providers that may offer independent scoring systems or event notification systems; however, with no accepted standard scoring methodology insurance companies can’t uniformly implement these varied scoring approaches. Furthermore, these scoring systems rely on a very limited number of variables which haven’t proven predictive of collisions, at-fault or otherwise. They have only proven useful in finding cohorts of businesses who are lower risk due to use of the TSP system over time and self-selection.

Similar to a credit score, factors in the FICO-like driving system are normalized and weighted so that different vehicles and different scenarios have a uniform impact on one’s score. From the credit rating agency you can receive a copy of your score in advance of your mortgage application and thus have insight into how you will be viewed, or normalized. Transparent and effective normalization of data is a key requirement to produce a commonly accepted driving score that provides significant value to institutions that rely on them.

All drivers, despite differences in driving responsibilities, types of vehicle, speeds driven, etc., must ultimately yield a standardized and comparable score. Just like you can trust a credit score of 750 to mean the same thing to different mortgage lenders, the vehicle insurance world could use that same concept of uniformity to rank drivers, assess risk exposure and streamline underwriting decisions based on a uniform scoring system. Different driving behaviors are weighted differently which gives insurers the predictive analytic advantage of where the risk is and which vehicles are most likely to be in an at-fault collision.

The FICO-like driving score goes beyond the traditional methods used to rate drivers because it analyzes actual driver behavior, every second of every trip. The parameters for defining risk assessment using a FICO-like system are multi-dimensional and on a much more granular level of analytics. Drivers are ranked on aggressive behavior, distracted behavior, overall driving tendencies and specific risky events that are most likely to result in an at-fault accident. And, while using considerably more relevant variables, this results in a much more easily explained score for driver feedback.

Some systems offer ‘events’ notifications as the alternative for driver feedback, but these are frequently discredited by the driver’s themselves because those events only capture a very small sliver of the overall driving picture. To pinpoint which drivers are the most at risk, the system must catch all the driving behavior between events. Accuscore has created the world’s first continuous monitoring system to address this deficiency resulting in the most comprehensive driver profile on the market.

Usage -Based Insurance

For Consumer Vehicles

Vehicle insurance underwriting is experiencing a paradigm shift to UBI. In Personal Lines consumer auto insurance 17 million people worldwide are expected to have tried UBI auto insurance by the end of this year. Much of the traction achieved in the UBI market, thus far, has been due to the nature of self-selection; namely, that good drivers are more eager to participate for the opportunity to pay less insurance. Insurers must now go beyond attracting good drivers only and implement tools with greater predictive capabilities to access broader segments of the market.

For Fleets of all Types and Size

Commercial lines auto insurers are looking for a different scoring system, one that encompasses all of their vehicles and drivers. These overall fleet scores take into account the operating characteristics and installed safety equipment on their vehicles, the environment in which fleets operate (road types, times of day, traffic dynamics, weather, etc.) and the aggregated driving behavior scores of all their drivers.

Heretofore, commercial auto insurers have been collecting a five-year claims history and reported miles on the fleets they insure to determine risk and renewal strategies. The new UBI fleet scoring standard capability now allows them to compare fleets of similar industries and territory to determine relative risk, leading to a strong desire to elevate the issuance and renewal process with more accurate means of underwriting risk assessment. The combination of direct measurement of driving behavior and contextual analysis of the driven environment significantly outperforms traditional rating variables such as age, gender, and credit scores when estimating risk. As commercial auto insurers well know, the sheer nature of risk is much greater in fleets, compared to the personal lines market, with associated higher premiums and anticipated payouts, often involving larger vehicles with more expensive loads and expanded legal ramifications.

Forward-looking commercial auto insurers are assessing their current business models in light of this more sophisticated risk analysis capability enabled through the use of analytics applied to telematics-generated data. Indicators suggest insurance actuaries are ready to adopt more driver behavior related indices. Such is the underwriting value of more predictive risk identification that many fleet insurers providing financial incentives to their insured’s to give them access to the driver and fleet scoring.

More than ever before, fleets have the opportunity to monetize the value of their telematics data at an increasingly lower incremental cost thanks to simplified data collection approaches such as Blue Tooth devices and smartphone apps. Further, on the commercial side, limitations and inherent flaws of the self-selection (opt-in) process are eliminated because drivers must adopt management policies, thus creating a more thorough view of insured risk of everyone.

Redefining UBI to RBI: Expanding Beyond Usage-Based to Risk-Based

The concept of UBI could better serve both the insurer and insured by expanding beyond usage-based to risk-based (RBI). Risk-based insurance would have strong correlators to underwriting risk and tell insurers a lot more than a record of how many miles driven, but rather ‘how’ those miles were driven and what is the associated risk per mile.

With the development of a standardized driver scoring system, RBI would be the perfect counterpart. As insurance companies look for a better way to measure exposure with current day technology advancements, the main selling points of transparency, accuracy and risk mitigation could contribute to the wide-spread adoption of a FICO-like driving scoring standard. Insurers looking to cut costs, improve business practices, and better assess clients’ risk levels, will increasingly invest in tapping into the data analytics that telematics enable.

With a better understanding, insurers will become more effective at identifying higher risk clients, allowing them to price-adjust accordingly or move that risk to another insurer. Carriers that don’t offer RBI will not be able to compete for the safest drivers and will risk losing their best policyholders.

In the new RBI auto insurance world, RBI insurers will attract and retain safer drivers. Consumers will benefit from more accurate policy rating and pricing from insurance companies that use RBI and standardized driving safety scoring. And both consumer and commercial drivers will be able to improve their driving behaviors by knowing their risk score and applying corrective action that will improve safety and positively impact their insurance rates. Implementing incentives for good driving will enable insurers to offer effective risk mitigation and driver improvement programs.

Who Owns the Score?

A FICO-like driving score delivers value to three stakeholders: the individual driver, commercial fleets, and the carriers who insure them. But whose score is it?

In the personal lines market, the consumer owns their personal driving score and the underlying data, and the consumer has the right to disclose the score as needed to obtain more favorable personal auto insurance. For commercial auto lines, where individual driver scores are aggregated to determine a fleet-wide driving safety ranking, the fleet operator owns the data and controls who sees the score and driving data, along with how the score and data are used, whether for safety improvement and loss prevention, insurance underwriting, self-insurance loss reserves, or claims management. The fleet owner may ‘opt-in’ to share driving data with insurers for preferential insurance coverage or service.

Bottom Line

Insurers want a standard data set, but they aren’t ready to just accept the score, they need the underlying data in a standard form. Consumers are ready for a standard score if they can be assured of transparency and location privacy. Telematics and safety technology advancements will have huge implications for the insurance industry over the next five years. Research indicates that commercial auto insurance companies are willing to pay 2-10% of annual premiums for accurate telematics scores to receive the value of better underwriting efficiency and risk mitigation capabilities. Further proof that a FICO of driving is transforming the auto insurance industry is the high probability this would most likely be a joint endeavor between the telematics service providers and insurance companies who are willing to cost-share in exchange for data.


A valid driving score would elevate underwriting by providing a uniform and portable scoring system that accurately predicts driver risk. Both personal lines and commercial insurers would benefit from being able to price risk more accurately, identifying the riskiest drivers, reducing accident frequency, and reducing exposure to risk.

Telematics and UBI programs are moving into the mainstream, despite numerous technological challenges and deficiencies. Turning raw driving data into actionable correlations is a major challenge facing insurers. If there were the perfect telematics scoring solution, universally applicable to risk underwriters, that could determine exactly how telematics data-points translate into a valid predictor of risk, it would open up a whole new perspective for the underwriting process. Market competition is forcing insurers to consider rating variables that outperform traditional proxies like age, gender, and marital status. Usage-based insurance (UBI) is at the top of their list. With a uniform standard of driver behavior scoring and analytics, insurance companies will be able to accurately assess driver performance based on actual driving habits on a risk per mile basis.

By 2020, over 50 million US drivers will have tried UBI insurance and the likelihood that a FICO-type driving score will be involved is inevitable. SAS predicts by 2020 over a quarter of all US auto insurance premium income will be generated via telematics, representing more than $30 billion. Carriers that don’t offer UBI or RBI are in danger of adverse selection because they won’t be able to compete for the safest drivers and policyholders.

Defining the New Standard… Risk per Mile Driven, Not How Many Miles Are Driven

Why is standardization important? Because when you adopt something universally for the purpose of comparison to others, there needs to be a defined baseline threshold to work from. In order to do that you need to have the same uniform standards across the entire pool. Imagine if FICO scores were calculated differently for different people, they wouldn’t have any true value. But because they are standardized and measure the same factors in the same fashion for all they make sense and provide significant value to institutions that rely on them. FICO thus represents advancement in both processes and technology.

Let’s Start With Consumer Auto Insurance

User Based Insurance, UBI, was adopted several years ago in order for the insurance company to basically get an accurate picture of how many miles drivers really drive. Some type of discount off of the insured’s premium is offered in order to get this data. Why you ask? Because miles driven has generally been the focal point that insurance companies have been able to use as a standard across the entire pool of drivers. Beyond that there are too many variables than can skew the picture and deform the concept of standards. So the premise, basically, is that more miles means more risk, to a great extent. They may also take into account time of day miles are driven as well as some rudimentary measure of driver behavior. For consumer insurance, these UBI programs are purely self-selective opt-in. To a great extent, this means the good drivers opt-in in order to get a policy discount, while the poor drivers have no interest in providing this level of detail. However, shifting the focus to true predictors of futures risk will yield great value to the insurer.

Now Let’s Consider Fleet Insurance

Similar calculation methodologies are used for fleets. However, drivers don’t have the luxury of opting in or out of any type of program the fleet and insurance company may create. The insurance company is mostly concerned with the risk of vehicle performance and overall safety of the fleet as a whole and not primarily with the individual driver. So it becomes incumbent on the company to address driver safety and training improvement programs in order to keep their fleet safe and their premiums lower. In addition to this, the better the driver, the lower the overall cost of operating the fleet is reduced as well. In the fleet world there exist GPS based fleet management systems designed to help fleets optimize their workloads, scheduling, routing, deliveries, and so much more. These systems use similar GPS devices to the ones used in consumer UBI programs. But each provider has their own scoring methodology (if at all). Thus there is no real ‘standard’ that can be applied universally across all pools of drivers across fleets. Therefore it becomes extremely difficult, if at all plausible, for insurance companies to leverage these systems for their purposes of underwriting and risk assessment as a meaningful standard.

Technology Evolution

With the advancement of technology it’s time to help the insurance industry evolve relative to data collection and specific types of data that benefits them and drivers alike. Being able to determine ‘how’ a driver behaves is even more vital that how many miles they drive. If you put it all together with the inclusion of contextual information, insurance can get a very accurate picture of potential risk associated with a particular driver or an overall fleet. Fleets can get much more accurate insights into which drivers drive well, and which ones expose them to the greatest amount of potential risk. Therefore, fleets can implement very specific driver improvement training programs and measure the trends accordingly. Software can help mine the specific and unique data related to driver behavior and risk and be applied to a predictive analytics model that can help define, shape, and improve potential future outcomes. Video systems are tremendous for capturing actual data at the time of an accident. They are the key to evidentiary proof as to what really happens, providing significant value in the area of claims settlement and accident exoneration. In most cases video solutions can help mitigate ‘claims’ reduction up to 40%. Simply put, that means reducing the payout because the video proved that the driver wasn’t at fault. However, driver behavior software can assess how drivers perform and hopefully mitigate the ‘accidents’ which are the cause of the related claims and costs. The challenge with video solutions has always been the extensive human involvement (and cost) required to review video clips and determine the identification of real risk and associated driver intervention strategies.) This is an expensive endeavor when you consider that only a very small portion of overall driving is actually evaluated. These solutions focus on the worst behaviors by the worst drivers, missing the opportunity for driving risk scoring across all drivers based on an evaluation of all driving behavior.

In Conclusion

Advanced driver behavior and risk assessment software provides many benefits not being realized today, by insurance companies, fleet management / telematics companies, and fleets alike –

  • Standardized and uniform report across fleet management systems
  • Accounts for actual driving performance and not just miles driven
  • Helps create the valuable data needed to create a true predictive analytics model
  • Adds value to implementing driver training and improvement programs
  • Perfect companion to video telematics solutions providing more efficient identification of risk
  • Fraction of the monthly cost compared to video managed service programs

Why UBI Is a Compelling Proposition for Commercial Fleet Insurance

The right approach to telematics and usage-based auto insurance continues to be debated in the personal lines realm, but the value proposition—and the business opportunity—is clear for commercial fleet insurance. By combining telematics, behavioral metrics, driver risk scoring, contextual data and video systems, insurers can build the next generation of insurance solutions for commercial fleets.

Fleet Insurers have been collecting the same old data, a five-year claims history and reported miles, to determine risk and renewal strategies. There is a strong desire to elevate the renewal process with more accurate means of underwriting risk assessment. Forward-looking Fleet Insurers need to assess their current business models in light of a more sophisticated risk-model emerging through the use of analytics applied to telematics-generated data.

Building a Case for UBI in Commercial Lines

Telematics based services are rapidly expanding beyond standard operational services to also cover more behavioral aspects. This enables fleets and insurance companies to gain a deeper insight into both very tangible and less tangible areas that have a significant price tag associated.

With a strong correlating driver risk identification system in place, fleets and insurance companies can gain valuable insight that will assist in accurate policy pricing, targeted coaching of poor driving behaviors and identification of employee behaviors that have a negative impact.

A Complete Picture of the Fleet Performance

The driver risk score should ideally be combined with other contextual data related to native vehicle risk, typical vehicle routes, weather and other environmental conditions. With all of those parameters known, the insurance company will have a complete picture of the fleet performance enabling a very accurate policy pricing that goes well beyond traditional 5-year loss history as the main indicator.

The contextual data elements are very difficult to modify by the fleet. They can buy modern and safer vehicles, and they can optimize the routes to minimize high risk locations, but those come at an operational cost. However, once the fleet gains insight into the individual drivers detailed behavior, they have an opportunity to instigate targeted coaching for drivers that have the highest risk. Because the monitoring systems are so accurate, the efficacy of the coaching can easily be monitored and appropriate HR actions taken if negative behavior is persistent. Since the at-fault accidents are occurring within a small group of drivers, and those drivers can be identified, the fleet can actively drive towards a better overall fleet score and hence lower insurance premiums.

New indicators also suggest that drivers identified with erratic driving behavior will have a tendency to carry that erratic behavior into other work related behaviors, so effectively the fleet management will have an additional tool for employee performance which leads to improved customer satisfaction and more efficient business operations.

A New Era for UBI

The driver behavior data is collected from standard telematics devices that are already installed or are installed specifically for this purpose. The additional cost to collect the driver behavior data and GPS for contextual data is a small increment over standard GPS tracking solutions; however, the potential gain is significant. Currently, there is some disparity in how data is collected; however, there are industry-wide efforts ongoing that will standardize the raw data collection used for scoring. Once uniform data collection is enabled, most existing telematics devices can be easily upgraded to provide scoreable data. One could argue that this enablement will kick-start the migration to commercial UBI. The barrier to entry is lower for commercial lines than personal lines, and the ongoing operational costs will be lower due to the data sharing with traditional telematics systems.

The combined driver behavior data and contextual data effectively bring a new era to UBI. Traditional UBI is predominately about how many miles a vehicle drives and very little about how those miles are driven. With better risk insight the program can appropriately be called Risk Based Insurance—RBI. We will know how many miles were driven and we know which risk each of those miles carried. Hence the underwriting accuracy vastly improves.

(Related: Does Smart Phone-Based UBI Adequately Assess Driver Risk?)

When fleets are equipped with coaching tools that can accurately address driver deficiencies, they are able to further influence the inherent risk of operating a fleet of vehicles.

The early adopters among the insurance companies stand to gain a significant underwriting advantage and it is entirely possibly that we will see new programs closer aligned with personal lines pay-as-you-drive programs, but specifically targeted for fleets where the price elasticity would be driven more by actual present risk, rather than by miles. There is a strong demand for more granular knowledge prior to the underwriting phase. If fleets had a tool to improve driver behavior, and could document it through a reliable real-time score, insurance companies would reward that.

Video-Based Systems

Fleets carrying passengers have traditionally been leaning towards video based systems because they are very efficient in accident reconstruction and claims settlement. Those video systems have also been used for driver behavior monitoring. In general they work quite well, but are by nature event-based systems and really only target the top 10 percent of poor drivers. The rest of the drivers ‘fly under the radar.’ A more elegant system would be one that combines the best of the two worlds: accurate driver scoring of the entire population and continuous video recording for liability purposes. In recent years, advanced vehicle motion analytics effortlessly pinpoint the most critical clips without ever looking at a single video clip. There are a plethora of low-cost continuous video recorders brought to the market. Combine those with a telematics solution and you have a low cost solution with all the benefits.

With new analytics solutions, more commercial lines insurance companies can take advantage of installed and future telematics devices to collect a comprehensive data set driving towards a full risk-supported UBI program with minimum incremental cost.

Posted on: https://iireporter.com/why-ubi-is-a-compelling-proposition-for-commercial-fleet-insurance/


Fleet Safety – Determining Risk Per Mile Driven

Fleets have a tremendous opportunity to lower accident rates as well as improve operating efficiency by implementing a comprehensive driver safety program. Software solutions made specifically for commercial vehicles ensure safe driving and preventive maintenance initiatives are easier to implement and more effective than ever before. A telematics program can be a simple way to gain valuable insight into your fleet — and yields a speedy and ongoing ROI.

Telematics based services are rapidly expanding beyond standard operational services to also cover more behavioral aspects. This enables fleets and insurance companies to gain a deeper insight into both very tangible and less tangible areas that have a significant price tag associated.

With a strong correlating driver risk identification system in place, fleets and insurance companies can gain valuable insight that will assist in accurate policy pricing, targeted coaching of poor driving behaviors and identification of employee behaviors that have a negative business impact.

Deployment of the most sophisticated “risk-based” driver behavior scoring engine will deliver a more accurate identification of risk and a more actionable path for correction. Implementing “big data” back-end analysis and necessary data compensations applied to every second of driver performance will have a significant impact on driver safety, risk underwriting, risk mitigation, and claims settlement efficiency.

Driver behavior data is collected from standard telematics devices that are already installed or are installed specifically for this purpose. The additional cost to collect the driver behavior data is a small increment over standard GPS tracking solutions; however, the potential gain is significant. By using continuous vehicle motion analysis, telematics-supported driver behavior data provides a driver’s risk per mile driven. This level of granular data can now rank drivers on aggressiveness, distraction, general driving tendencies and specific risky driving events and come up with an overall driver safety score.

Having an accurate picture of driver behavior status is the prerequisite to effectively improve behavior and lower exposure to risk. There is a clear link between a well-managed vehicle fleet and profitability. Employees injured in a motor vehicle accident can have a negative effect to a company by incurring costs such as lost production, workers compensation, replacement costs such as new staff and equipment, insurance premiums/increases and a potential burden of civil lawsuits. But the huge financial burden and human cost of road crashes goes far beyond your workplace.

In 2013 the NSC documented the estimated cost of motor vehicle deaths was $267.5 billion. With more than 90 percent of crashes caused by human error (per the National Safety Council or NSC) creating a Fleet Safety plan will help achieve a desired level of safety.

Unmanaged drivers vary greatly in their safe driving skills. Even good drivers drift into poor safety habits over time. Positively impacting a fleet’s exposure to related risk must begin with identifying and positively modifying driving behaviors.

In the U.S. there are:

  • 10 accidents every minute.
  • Five vehicle-related fatalities every hour.
  • One-quarter of a trillion dollars is spent annually on collision claims.

As settlement and legal costs continue to escalate, the costs to fleets are tremendous and often avoidable through improved driver behavior. The greatest reductions in risk are made by intervening with the drivers that are farthest from the desired driving skill level. It remains important to give all drivers continuous feedback regarding their status and changes in driving behaviors.

All drivers represent a certain degree of risk and an opportunity for improved driving. As well as understanding the skill sets of the fleet drivers, every driver and manager of the fleet should understand the documented expectation of what good driving looks like. Only when the desired model is presented, can deviations from the desired norm be acted upon.

Only by defining the “desired norm” of driving behavior, can the fleet document variances from the norm and act accordingly to improve these variances. The goal of improving driver behavior is to have each driver execute his or her driving responsibilities at a desired level of competency.

Fleets carrying passengers have traditionally been leaning towards video based systems because they are very efficient in accident reconstruction and claims settlement. Those video systems have also been used for driver behavior monitoring. In general they work quite well, but are by nature event based systems and really only target the top 10% of poor drivers. The rest of the drivers ‘fly under the radar’.

A more elegant system would be one that combines the best of the two worlds: accurate driver scoring of the entire population and continuous video recording for liability purposes. In the recent years, there has been a plethora of low cost continuous video recorders brought to the market. Combine those with a standard telematics solution and you have a low cost solution with all the benefits.

Article also posted

Does Smart Phone Based UBI Adequately Assess Driver Risk?

An increasingly plausible option for usage-based underwriting is to combine a low-cost Bluetooth-enabled data collection device with a smart phone app in order to satisfy both quality data and customer intimacy for personal lines insurance.

Many insurance companies today, personal and commercial alike, have engaged in usage-based insurance underwriting. There are two ways of collecting the use information from the vehicle: One is using a telematics datalogger and the other is using a personal smart phone with an app running in the background. Both work reasonably well for collecting miles driven and time of day; however, if the underwriting includes any form of driver behavior data, the hard mounted device provides a superior data set.

Now, the real question is what data set provides the best correlation to actual underwriting risk. Assume that it was possible to generate a valid driver behavior risk score in conjunction with miles driven. Would that data set have more value in the underwriting process and is it cost effective? Naturally, the total cost of using an app on the user’s smart phone will have the lowest possible data collection cost. But what if the data cost of the valid driver behavior risk score was only incrementally higher, would it be the obvious choice?

One of the problems with the detailed driver behavior risk score is that it requires high quality data processed by capable servers. Therefore, until the vehicle can provide quality accelerometer data from the head unit we have to rely on plug-in devices to collect the data. Current plug-in devices are predominately uploading data via an internal cellular modem. The cost of the modem and the cellular transmission makes this solution relatively expensive. There are several vendors currently working on cost-optimized Bluetooth only devices where the datalogger cost is close to half of the cellular datalogger and the data will be transported by the user’s smart phone. This will enable high quality data collection at minimum cost.

For commercial vehicles, the existing telematics dataloggers can have a dual role as both GPS tracking/operational efficiency tools and as data collection for insurance underwriting purposes and hence the cost burden is acceptable. For the personal insurance market, the jury is still out what the right implementation should be. The smart phone app is a great marketing tool for the insurance companies, but the quality of the collected data is very poor. Recent articles on the subject suggest that the UBI path going forward should focus on easy to use smart phone apps; however, the challenge with that is data quality. Smart phone apps cannot collect motion related data (driver behavior characteristics) and barely get actual miles driven or time of day.

Although the most refined apps have worked out major kinks and no longer drain smartphone batteries or require policyholders to press “start/stop” to track every trip, the data quality from the smart phone is not good enough. The smart phone’s obvious inability to always be present and actively recording when the car is driving leads to significant data gaps. Any form of true driver behavior can not accurately be collected via smartphone. Therefore, one increasingly plausible option is that a combined solution of low cost Bluetooth enabled data collection device and a smart phone app will satisfy both quality data and customer intimacy for personal lines insurance.

When UBI Self-Selection Ends

Mobile UBI advocates tout that policyholders can simply download the free branded apps from the app store, virtually eliminating the upfront equipment costs for insurers. While this is true, what is not mentioned in these articles is that UBI is still in the voluntary or self-selected phase, meaning policyholders elect if they want to participate or not. People who are willing to use the smart phone app are already good drivers that would most likely volunteer for a UBI program in the first place. Once this self-selected honeymoon phase wears off, and we get past the initial pool of good drivers, you need data accuracy.  We have not gotten down to the population yet that have driving issues because they don’t opt in to the program, but once they do, the poor data collection devices will face a serious challenge in proving underwriting efficacy.

Article from:


Acculitx Receives $1 Million in Series A Funding

By BRAD GRAVES Thursday, July 2, 2015

Acculitx, formerly known as Fleet Matrix, said on June 30 that it received $1 million in series A funding.

The firm providing the funds was 9411 Associates LLC, a group of San Diego-based investors.

Acculitx is a 3-year-old company which decided to change its name about a month ago, said co-founder Alan Mann. Its core product is accuscore, which the company bills as the world’s first meaningful driver profile score based on actual driving performance.

“Fair Isaac provides a comprehensive FICO score for credit rating, similarly, we provide a comprehensive score for driver behavior and risk,” Mann said in a prepared statement.

Two former DriveCam employees — Peter Ellegaard and Mann — are at the helm of the company, which has eight contract employees. The company hopes to increase permanent staff with the new funding, Mann said.