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?”

Conclusion

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/

Accuscore Announces Specialized Separated Driver Risk Scoring for Insurers and Fleets

Accuscore, a provider of the unique driver scoring system that provides the most accurate and risk-predictive driver behavior analysis, now offers a separated scoring function, based on the same collected driving data, 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.

San Diego, CA July 12, 2017 – 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. This type of 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.

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.  It is not fair for the driver to be penalized for factors beyond their control and yet the insurer benefits from the additional insight of the risk of the driven road.

Accuscore’s in-depth, second by second motion analysis, with multiple compensations applied to each second, achieves the sensitivity of scoring that allows us to isolate the “pure driving” score from the effects of varying road characteristics.

According to Alan Mann, President of Accuscore, “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.  The fleet and the insurer have different needs in terms of scoring insight to fully monetize the value of driver scoring.  Accuscore uniquely delivers that optimized view of driving risk to both fleets and insurers.”

About Accuscore

Accuscore is a San Diego-based company specializing in more accurate driver behavior scoring.  Commercial insurers receive more risk predictive underwriting insight.  Fleets receive an effective loss prevention/driver behavior tool to identify and correct issues related to risky driving behaviors.

For more information, contact Alan Mann at amann@acculitx.com

Why Consumer UBI Approaches Just Don’t Cut it for Commercial Insurance

Plus, Key Questions to Ask Regarding Driver Scorecards

The use of UBI approaches to commercial insurance necessitate a very different approach than the typical consumer UBI that we are all familiar with. Commercial use of UBI technology needs to identify very different factors of driving risk to help achieve underwriting insight and provide the foundation for an effective loss prevention program. Commercial insurance applications have been slow on the uptake thus far because vendors have simply not delivered required value to commercial insurers. This value is clearly the predictive risk associated with driving behavior. This is the missing piece of underwriting insight for commercial insurers. Just how different are commercial and personal lines solutions?

Commercial vs. Personal Lines UBI

Unlike personal lines,

  • Commercial risk prediction is not aimed at delivering a “discount” to the opt-in (self-selected) participant. Value is delivered in terms of incremental underwriting insight for the insurer as well an effective loss prevention tool for the fleet. Potential financial participation of both the insurer and the fleet are enabled as the insurer receives underwriting insight and the fleet is enabled to implement an effective loss prevention program.
  • Commercial application typically involves mandated full participation by the driving population, allowing all fleet drivers to be compared to one another and all fleets to be compared, allowing the insurer effective comparisons of companies across their book of business and allowing fleets effective comparisons amongst all of their drivers.
  • Commercial application is more focused on highly accurate driver risk prediction for underwriting insight. Driver behavior is the most actionable incremental insight the insurer can use to accurately predict future risk.
  • Commercial insurance is more focused on higher value, higher premium vehicles, with much higher loss experiences, thus a more attractive and attainable ROI is associated with effective loss prevention programs and risk identification and ultimately, improvement in loss histories.
  • Commercial insurers desire device neutrality so insureds can use their customer’s chosen technology (telematics device, video camera, smartphone App) while still providing underwriting insight to insurers. The smartphone delivers the added value of being able to be delivered across the insurer’s entire book of business at an attractive price whereas individual devices will never provide a telematics view across all insureds.
  • Commercial insurance is more focused on loss prevention efforts of fleets, while there is little focus on driver improvement with personal lines solutions. Insurers may commonly incent/co-fund loss prevention initiatives of fleets since fleets and insurers benefit through improved fleet loss experiences. Motivation/incentive for driver improvement are driven by fleet safety as well as the insurer in commercial applications. In consumer applications, motivation is typically related to a discount in insurance cost, a status only a minority of drivers will even qualify for.
  • Commercial auto is a loss leader, increased volume does not move the profit dial, accurate identification/removal or appropriate pricing of worst risks does. Thus driver risk profiling and associated risk pricing are much more important to commercial insurers.
  • Just like personal lines, negative customer selection is a huge motivation to accurately identify fleet and driver risk exposure—let your worst risks go to your competition (or price them appropriately).

Achieving More Risk-Predictive Scoring

Understanding that the commercial fleet insurance space is far different than the consumer space and that the focus is much more clearly on the identification of driving risk, there are key questions that should be answered in regard to the ability of various solutions to deliver a higher degree of risk-predictive value associated with driving behavior.
The understanding of actual driver behavior is typically the missing piece in the insurer’s quest to underwrite future risk. Industry actuarial insight is available, specific customer loss histories are available, it is a fairly simple process (and typically already done within the insurer’s actuarial skills) to determine the “risk of the driven road,” i.e.—what is the risk impact of roads, road conditions, weather, time of day, geography, and inherent safety of the vehicle. The missing piece in the underwriting equation is the differentiator between similar types of insureds—namely, driving behavior calculated accurately.
Since most TSP/video/smartphone Apps that seek to monetize the value of telematics data do that on the basis of questionable logic associated with risk determination, the insurer should understand the real predictive value of risk associated with driving and what kind of data processing is required to deliver that improved data.

track-fleet-gps

Key Questions to Ask Regarding Driver Scorecards

While all drivers are certainly not created equal, it may not be so obvious that all driver scorecards are also not created equal. There are very significant differences in scorecards which directly impact the actionable nature of the scoring and the predictive risk value that they offer. The world is in a rush to “monetize telematics value.” The value of telematics data is directly related to its ability to accurately predict risk, namely associated with driver behavior.

With all of the vast potential associated with the identification of driver risk through the interpretation of vehicle motion, it seems like the cornerstone of insurance telematics assessment ought to be the accuracy of the identification of risk. In reality, however, we find very little questioning or understanding of the accuracy of the typical driver dashboard.

This guide attempts to give a framework for understanding the accuracy of driver scoring solutions and aims to identify the type of scoring that insurers can count on to be most predictive of future driving risk, hence the optimal tool to use as an additional tool in underwriting operations, pre-renewal processes, and loss prevention programs.

Driver scorecards are available with virtually every solution from video providers as well as telematics suppliers (TSPs). These scores attempt to show risk associated with risky behavior predominantly identified from vehicle motion. These determinations are typically made either from accelerometer data or by calculating changes in speed/momentum over time. Customers wanted more insight into identifying and correcting driving risk. TSPs, typically relying on telematics devices provided by a small group of suppliers, used the ability of the device to set an arbitrary g-force level which allowed them to keep track of how many times a driver exceeded that g-force level. This became the foundation of the identification of a “risky event.” The threshold for the g-force level would often be set to record a “manageable/reportable” number of such events, again an arbitrary distinction based on expediency. From a safety perspective, it was concluded that the number of times a driver exceeded an arbitrary g-force momentum change was a good depiction of that driver’s risky driving.

When speaking of video solution providers, early market leaders relied on the marking of an erratic event (determined by a g-force level being exceeded) to be retrieved later and used as the basis of corrective driver feedback. They also sought to make a real time determination of what level of g-force threshold would determine a risky event and then commit a small video recording before and after the “triggering event” (the g-force level being exceeded to cause the event to be recorded). With declining costs, it became possible to continuously record video data, but the concept of marking relevant events is still pervasive, so the fleet has a tool to get at the most relevant video examples more efficiently.

So what’s wrong with this? While “good enough” or “better than nothing” scoring has been pervasive, it is not accurate enough to be relied upon to accurately predict future driving risk based on past performance. Applying better science to the interpretation of risk is not significantly more expensive, it is just better. Better science creates more predictive risk for insurers and the basis of a more accurate loss prevention/driver behavior improvement tool for the fleet.

When Evaluating Driver Scorecards and Their Accuracy, The Customer Should Ask the Provider of the Driver Scorecard the Following Questions:

1. How do you define a risky event? If the event is determined by exceeding a simple g-force or delta v/delta t calculation, the inherent inaccuracy is easy to define. Accelerometers or delta v/delta t calculations determine the relative change of vehicle momentum and correlate that to risk. accuscore-fleet-gps2The issue, however, is that it is very easy to achieve a significant change in relative momentum at low speed. At high speed, you can have a very significant braking event, for example, but the actual change in relative momentum is relatively small. This results in a preponderance of low speed events and very few high speed braking (for example) events. This is exactly the opposite as it should be since higher speed events are inherently riskier. And speed is only one of the variables that needs to be properly compensated for to achieve accurate driver risk scoring.

2. When your vendor speaks of a driver safety system, what is the focus of that program? Often vendors will quote improvements in speed management or the identification of non-driving (contextual) events as important to driver scoring. The essence of driver scoring should be the identification of risk brought into the picture specifically around how the driver drives. Correlating location information to contextual insight (what is the weather, time of day, road conditions, accident history of road, inherent safety of the vehicle, etc.) has value but these are all factors that the insurer has evolved internally over many years. From a safety perspective, there is very little that you can do to address the “risk of the driven road”. The vast majority of opportunity is tied to correcting weaknesses in driver behavior and that can only be done through the most accurate assessment of risk possible.

3. Does your vendor talk exclusively about g-forces or is it understood that changes in momentum are not necessarily significant unless understood in the context of the entire driving situation? The focus should be on energy displacement, not the exceeding of a pre-determined momentum change threshold. Energy displacement cannot be determined real-time at the device level; continuous “big” data must be interpreted on the back-end to apply all appropriate compensations to yield the most accurate risk scoring.

4. Does the solution identify severities of events? If you are just declaring a risky event to be correlated with the exceeding of an arbitrary threshold, you are basically then keeping a tally of how many times that threshold is exceeded and coming up with a driver risk score based on that. Your safety program does not exist below that arbitrary threshold and there is no segmentation of event severity above that arbitrary level. The problem is that there is a whole lot of difference between having an event that exceeds a certain threshold and the less frequent really REALLY dangerous event. You want to know the difference. In insurance speak, most driver dashboards give you a driver risk score on (poorly defined) frequency only; there is no ability to understand the true severity of any particular event. If you are not making appropriate compensations to data, there is no way of knowing the risk of an event based on a g-force reading. It is very possible to have a more dangerous event at .06 g-forces in comparison to another event at .08 g’s. Knowing both the frequency and severity of events is critical to determining risk and this only done by understanding the entire context of the driving situation.

5. Does the system identify your best drivers as well as your worst? Typical telematics solutions use the (flawed) calculation of driver risk but can at least generate a score for each driver. Many (especially video oriented) solutions focus on identifying the worst examples of risky driving and intervening aggressively with those drivers. The problem with that is that there is little reporting/feedback available to the masses for them to understand their behavior and make the subtler corrections that might improve their driving safety. Driver acceptance of the overall program is greatly enhanced if a preponderance of drivers actually receive feedback about how good they are. Good drivers also take pride in this aspect of their performance and make an even greater effort to improve their scoring. While it does not create as much movement in the total overall company risk, every bit of improved driving helps and is important in positive acceptance of the program in the fleet.

6. Specific compensations have to be made to data to create an accurate depiction of risk. Earlier, we mentioned that a change in vehicle momentum is only relevant if you know the exact speed of the vehicle exactly when that event happened. In similar fashion, it should be understood that a heavier vehicle takes longer to adjust to any given driving situation or requires more braking energy to stop in the same distance; that it’s kinetic mass delivers more destructive potential, etc. Therefore, the weight of the vehicle is needed to be able to make a determination of what safe driving looks like. The heavier the vehicle, the smaller the margin for error, so the scoring must be more critical of heavier vehicles going through the same circumstances at the same speed, with the same degree of momentum change, etc.

7. Does the system compensate for trip length? A bias toward better scoring will be associated with a long uneventful trip (2 hours on a freeway with good traffic flow) than with a shorter stop and go kind of trip. Is there a method of normalizing those two trip results so they can accurately be compared from a safety perspective? How do you do that; how is a favorable bias toward longer trips compensated for?

8. Does your scorecard take into account duration of the event? If you are “event based” (looking to declare an event real-time at the device level), there is no view of the overall risk associated with the longer duration event. Example would be a long braking event with no particular moment exceeding a threshold level. Second by second analysis will offer the potential of identifying the risk in that one second, interpreting the risk of the next contiguous second, determining if that is a continuation of the event, and adding the total risky segments to arrive an overall risk score. In an event-based system, at no one point in time did you necessarily exceed the pre-determined threshold level, hence this wouldn’t even show us as an event.

9. If you are relying on accelerometers to determine momentum change, are you sure those x, y, and z readings are accurate? A small distortion, or drift, in those readings can cause significant misinterpretation of data. How do you determine if accelerometer data is true?

10. In the interest of expediency, most driver scorecards and risk prediction programs rely on an “event” to be captured real time at the device level. More accuracy is achieved through evaluation of continuous data samples. Is your vendor delivering event summaries or is complete data fully evaluated on the backend? From a “change in momentum” point of view, even on second samples contain a lot of noise, therefore typically requiring sub-sampling within the one second. How does the solution balance the need for accurate driver risk prediction with an economic data approach?

11. Is your smartphone App really smart? While the potential use of smartphones is obvious for large scale commercial deployments, there are really only a handful of smartphone App providers that have the capability to effectively use smartphones to generate the data needed to do sophisticated scoring. These providers apply advanced artificial intelligence and signal processing to differentiate between motion related to the actual vehicle vs. motion of the smartphone within the vehicle. How is the determination of risky driving behavior/events made with the use of the App?

Summary

With an event-based approach to driver scoring, all momentum change conclusions are flawed to some degree. They may create a rough picture of driving risk, which is better than nothing, but you can do much better. For maximum accuracy of driver risk prediction, continuous data should be interpreted on the back end so appropriate compensations can be made allowing the risk associated with changes in vehicle momentum to be accurately determined. Compensations must be made to guarantee integrity of data and determine risk of momentum changes in the context of the entire driving situation.

Alan Mann is President of Accuscore, a San Diego-based company specializing in the accurate determination of driving risk through the application of superior science. More predictive driving risk enables commercial insurers to underwrite better while also enabling the fleet to implement a cost effective and efficient driver behavior improvement program.

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.

Smart-PhoneApp-for-Fleets

Solution

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.

 

Building the Perfect Usage-Based Insurance Mobile App

The ideal app would use all the sensors available in the phone for data collection, including GPS, gyro, heading, and accelerometer. Smartphones have not been capable of generating the quality of accelerometer data needed for accurate scoring, but that will soon change.

Insurance carriers already know that smartphone apps, email, and online chat lead to higher customer satisfaction. The rising popularity of smartphones has also led many insurance companies to build versions of their websites optimized for mobile browsers and to offer dedicated apps that allow users to get quotes, submit claims, and manage their policies. Mobile apps for usage-based insurance (UBI) add another element to a market that has previously relied on small devices plugged into onboard diagnostic ports. Smartphones have the capability of connecting tens of millions of drivers to UBI services.

Insurance companies are unveiling mobile apps that gauge driving behavior through smartphones to set insurance discounts and renewal strategies for motorists and fleets. There is huge momentum and excitement around the use of smartphones as enablers of information flow to be used in UBI and risk identification. The value of the smartphone, of course, is that virtually everyone has one, and the incremental air time to transmit data is a trivial expense to the user. Thus, smartphone apps represent a potentially free resource which can be used to improve insurance risk prediction, a significant cost departure from previous UBI programs.

UBI programs that rely on data from smartphones will be the rule rather than the exception in the not so distant future. However, the adoption challenge is two-fold: first, the accuracy of smartphone data must be on par with the same readings from a plug-in device; and secondly, the smartphone app data must be integrated with other data to yield the most accurate prediction of driver risk. Future smartphone apps will also be able to focus on improving driver performance in an effort to continually increase safety, reduce risk, and thereby reduce costs associated with collisions—and all this with superior accuracy. It’s a tricky technical challenge; but it can be done.

Current Approaches to UBI Data Collection

Currently insurance carriers have two options for gathering data for UBI. Most personal lines insurance companies are using a plug-in OBD device to capture driving data.  While this approach offers superior data collection quality for the most accurate underwriting, plug-in devices are costly to the insurer and inconvenient for the user. Increasingly, insurers are moving to a smartphone-based solution for their lower cost structure and ease of distribution; however, the data stream of the current crop of smartphone apps is rather poor compared to the plug-in device, so data quality is sacrificed.

Many telematics systems use speed to derive acceleration events by taking the second-by-second speed delta as an approximation for acceleration, using GPS as the speed input. A correct speed calculation requires that the speed information is accurate both in mph and in time. If either is slightly off, significant errors can occur. Challenges arrive in urban canyons, forests and tunnels where GPS signal erodes or disappears all together. Significant errors will occur on the speed data.

Most current smartphone apps are not collecting accelerometer data off the cell phone; the data is derived directly from the GPS feed.  Additionally, only using GPS to determine trip start and end requires the smartphone to frequently run the GPS to determine if a trip has begun. This causes significant battery drain, so the typical application will only be able to sample the GPS every few minutes and hence often miss trip starts. A lot of the data collection problems will go away when the smartphone apps collect accelerometer data off the phone and have persistent data collection. The ideal app would use all the sensors available in the phone for data collection including GPS, accelerometer, gyro, and heading.  A multi-sensor approach allows for minimal reliance on GPS for location determination.

Challenges of Current Mobile UBI Apps

Although insurers have reached important milestones in terms of mobile UBI apps, customer reviews are a good indicator of the challenges these pioneers continue to face. Poor data collection from current smartphone applications causes customer dissatisfaction, leading to contact with customer support departments to file complaints about miscalculated data that includes inaccurate trips, mileage, and events, which also adds to the overall cost burden.  The poor data also impedes underwriting efficiency.

Most Common Complaints about Current Apps

Most Common Complaints

Online reviews have a consistent mixed theme: customers like the idea of the app, and think the concept is great and like the look and feel, but complain about accuracy, lost trips and battery drain.

“I like the concept of the app, but I don’t like the fact that when I am driving the app is constantly searching for my location draining the battery. I have never had to keep my phone constantly on the charger. It would be nice if it didn’t drain my battery.”

“Good look and design, but doesn’t record all of my trips so I am missing out on points. Sometimes it works but 9 out of 10 trips are not being recorded.”

“I really like the app. It’s a great idea to give incentives to make people drive safer. My only issue is that the app crashes all the time. I’m lucky if I get my trip saved before it crashes.”

What are the Requirements of the Ideal Insurance Mobile App?

Chart Mobile

  • Accurate Data Collection: Trip start and stop times; miles driven; time of day; meaningful driving events; and data for driver behavior score. By leveraging the technology in the smartphone, the app would detect driving within seconds of beginning a trip. Setting the smartphone in motion triggers the smartphone accelerometer and the application starts recording the activity right away. When the activity ends, the app falls back in to hibernation.
  • Multi-sensor data evaluations: allows for minimal reliance on GPS.
  • Ability to detect both slow behavior changes and rapid changes, such as a crash.
  • Low Battery Consumption: Typical use would consume under 8% of smartphone battery on a daily basis.
  • Automatic Passenger Trip Cancellation: If app is running on both the driver and the passenger phones, back-end will cancel trip gathered most likely by passenger.
  • Automatic filtering for anomalous in-vehicle device movement: Detects when the driver is moving the smartphone vs. movement of the vehicle, and able to generate viable accelerometer data even from a non-fixed mount phone.
  • Commercial: Ability to automatically assign trips to company account and personal account according to on-duty schedule and allow further on/off shift adjustments.
  • Continuous Driver Behavior Monitoring: Not simply event-based data collection.
  • Optional Behavior Based Coaching: Implement targeted driver improvement programs and address issues quickly. Identify other patterns of poor driving, not just events.

How Can the Ideal App Be Used?

Telematics-based insurance can finally gain traction, because instead of requiring physical devices that must be manually installed in a car, the data required can now be collected through mobile-phone apps that are much easier to download and install. Customers in every market are migrating to smartphone apps including personal lines insurance, commercial insurance, and fleet management.

Who Will Benefit?

Personal Lines: As a replacement for plug-in devices.

Commercial Lines: Paradigm shift for commercial underwriting because the driver behavior score can be summarized to company level along with total miles driven and therefore contribute in the underwriting process.

Fleet Level: Even without insurance participation, a fleet manager can use the app to monitor and improve driver behavior at a very low cost.

SUMMARY

Mobile devices and smartphone apps are leading-edge tools that most people own and are the key to big scalability for insurers’ UBI programs. As data collection using smartphones improves, insurers will be better able to align their strategy with the smartphone as the primary data collection point making it the superior choice. The most successful mobile UBI apps will be those that integrate multiple smartphone sensors, profile a driver’s risk to the most accurate possible level, and make the overall experience better for the customer. Penetration will keep up with evolving technology as limitations are overcome. Superior science applied to more accurate prediction of risk would decrease collisions by identifying which drivers are most likely to be in an at-fault collision. Superior technology applied to data collection via smartphones would increase customer loyalty.

In the interest of an expedient solution, insurance carriers have been delivering deficient scoring of driver risk and settling for good enough. With accurate data collection, the ideal app will have the ability to generate traditional UBI information including trip start, trip end, miles and time of day. Furthermore, due to highly accurate accelerometer data, the app could also collect driver behavior throughout the trip in continuous mode and move away from the simple event-based systems to a more meaningful understanding of driving trends and habits. A continuous monitoring system would greatly improve the driver behavior assessment and hence risk assessment of each mile driven. Smartphones have not been capable of generating the quality of accelerometer data needed for accurate scoring, but that will soon change.

(Image credit: Dollar Photo Club.)

Posted on: https://iireporter.com/building-the-perfect-usage-based-insurance-mobile-app/

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.

ARE U.S. INSURANCE COMPANIES READY FOR A STANDARDIZED DRIVER SCORING SYSTEM?

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.

 

HOW IT WORKS

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.

Summary

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

Measuring the Right Data… Driver Behavior and Risk Assessment

Today, everyone knows that it’s important to measure what you manage and manage what you measure. That’s great, but let’s consider this… what if you’re measuring the wrong data? Or at the very least, measuring data that does not truly give you the accuracy you think you’re getting? More to come…

When GPS first was introduced to the mainstream commercial markets it was wonderful. Companies for the first time could see their field assets locations. They were empowered! Now what? Knowing where your assets was great, but then came the next level of questions… “What do I do with that data?” And so it began, the evolution of today’s modern fleet management systems and other similar telematics enabled services. We are now seeing the forward progress move into virtually every vehicle, device, and even pet.

Now, let’s consider the first paragraph again, measuring and managing. The topic is about driver behavior, safety, and risk assessment / mitigation. Today’s fleet management and telematics programs deliver a tremendous amount of value to every business that deploys them. It’s become critical to have one in order to maintain maximum productivity and to stay ahead of competitors. One of the functions many systems have today is ‘Event Based’ tracking of driver behavior. This enables a fleet supervisor or other key member evaluate, both in real-time or after the fact, how many times a driver performed a harsh-braking maneuver, or harsh acceleration, or aggressive turn. And this is good… sort of. Events give you only a sliver of information that an event occurred. But what it doesn’t tell you is anything about the event itself, if it was a severe or very minor event, or the duration of the event. Also, what event based systems don’t tell you is how the driver performs when there are no events. The assumption is that they drive well, but how well? How do they compare to the other drivers in the fleet? You can start to see that measuring and managing those ‘events’ can possibly be an exercise in measuring data that does not really tell you the true or accurate story. It’s like measuring birthdays. It’s great to know you had 50 of them, but which party was the best, or worst? How well did they live each year between birthdays? Knowing the count doesn’t really tell you the real story.

With the evolution of technology so comes the promise of newer and better software and resulting data. We’ve all been witness to newer, better, faster, unique applications on the market. Just look at your hand-held device. Because we’ve measured things one way before doesn’t mean we have to keep doing it the same way if there is something better and available. Many are aware of the UBI Insurance programs that are offered to individual consumers today. Put in an OBD device in your car and let the insurance company get information about how you drive. Only problem is that it’s self-selective, meaning only the good drivers are opting in due to the potential discount via some type of ‘loyalty program.’ In general, they only measure how many miles are driven, time of day, and maybe speed. The movement afoot is to further the evolution of UBI to what we are calling RBI, Risk Based Insurance. With the further advent of very detailed and accurate driver behavior software, being able to assess risk takes on a whole new meaning for both fleets and insurers.

Specialty fleet insurers are showing genuine interest at the prospect of having driver scoring software that provides them with details that are expressly related to driver behavior and potential risk assessment. There have been significant discussions regarding their interest in potential cost sharing, which often times can cover much, if not all, of the cost for the entire program. Consider that the cost of insurance premiums for a fleet driver potentially being on the magnitude of 2-3x or more on a yearly basis when compared to the average consumer, especially since the cost of claims can proportionally much higher. Not to mention fleet vehicles can be much more expensive to fix after being in an accident. In addition to all of this there may be a reduction in maintenance related costs for vehicles driven by better drivers, as well as a reduction in the overall fuel expenses. Add all that up and you have much more of a reason for fleets to invest in understanding and improving their driver behavior. When you combine a new driver scoring model along with the proper driver training and improvement programs you get a very sophisticated and effective way to safeguard your drivers, your vehicles, and corporate assets. If you’re going to invest your time managing metrics related to your driver’s performance make sure you are not measuring just a very small slice of the overall picture. Much like a puzzle, one piece doesn’t show you the full picture.