Tag Archives: arity

5 Steps to Understand Distracted Driving

For anyone involved in vehicular transportation, it’s accepted that distracted driving is a deadly problem that needs continued attention. Earlier this year, the National Highway Traffic Safety Administration (NHTSA) published a detailed research report on Distracted Driving in 2016. According to the NHTSA’s statistics:

  • Nine percent of fatal crashes in 2016 were reported as distraction-affected crashes
  • In 2016, there were 3,450 people killed in motor vehicle crashes involving distracted drivers.
  • Six percent of all drivers involved in fatal crashes were reported as distracted at the time of the crash.
  • Nine percent of drivers 15 to 19 years old involved in fatal crashes were reported as distracted. This age group has the largest proportion of drivers who were distracted at the time of the fatal crashes.
  • In 2016, there were 562 nonoccupants (pedestrians, bicyclists, and others) killed in distraction-affected crashes

Notice that teen drivers are the largest proportion of drivers who were distracted at the time of fatal crashes. However, a recent Arity survey shows that millennials are significantly less likely than the general population to say that “I never multi-task while driving” (48% vs 57%). What does this say about that demographic? With National Teen Driver Safety Week approaching at the end this month, it’s important to fuel this age range with the danger that distracted driving imposes on them.

Here at Arity, we used our own data to compare the rate of smartphone penetration in the US, with distracted driving activity of telematics users and industry losses. Our research goes a step further to demonstrate that this problem is only getting worse. The percentage of losses attributed to distraction over the last several years has tripled, costing the industry an estimated $9 billion annually.

See also: Distracted Driving — an Infographic  

The insurance industry has taken a multi-pronged approach to reduce distracted driving. In addition to high-profile campaigns designed to raise general awareness of distracted driving, such as AT&T’s #ItCanWait initiative, distracted driving solutions have been developed by insurance providers, OEMs and shared mobility and telecommunications companies.

As these solutions get closer to reality, there are a few core elements to consider. Here is a five-step process for the creation of a superior recipe for distracted driving detection:

  1. Mobile Phone, No Substitutes: While embedded systems and OBD devices are the gold standard for assessing vehicular motion and risky driving patterns, today there is no substitute for the mobile phone in distracted driving detection. The mobile phone is the leading culprit fueling higher rates of distracted driving accidents. Pinpointing mobile phone movement and interaction is the most robust way to identify and prevent these risks.
  2. One Part Movement, One Part Interaction: Phone movement only reveals part of the story. Distracted driving algorithms that rely solely on sensor information―accelerometer for translational motion, gyroscope for rotational motion, gravitometer for orientation, etc.―will be subject to false positives and false negatives. For instance, a motorcyclist with a phone safely in his pocket could be unfairly penalized each time he puts his foot down at a stop for balance.
  3. Measure Each Ingredient Carefully: Not all forms of distracted driving are equally risky. Checking navigation while stopped at a traffic light is generally less risky than taking a selfie while speeding down the beltline during rush hour. To effectively assess relative risks, there are two fundamental considerations: context and mode. Context means, what were the conditions present at the time of the distracted driving behavior? At what speed was the car being driven; what was the weather like; was there traffic? Mode means, what distracted driving behaviors were taking place? Phone call; texting; navigation; gameplay; etc.
  4. Monitor Continuously: Discrete or instantaneous markers only tell part of the story. For instance, counting only moments of large phone movement omits important information about the behaviors that took place interstitially. We can conceptualize distracted driving in terms of continuous sessions and endeavor to identify the starts and ends of these sessions. The total duration of distracted driving will provide the most predictive metrics for risk.
  5. Modeling Bakeoff: Distracted driving models can be founded on logic and intuition, but they should be developed and validated with a data-driven approach. For the best solution to emerge, many alternatives should be assessed relative to their performance on labeled data sets―data sets composed of both telematics data as well as reliable labels for the periods of distracted driving. An example of this blended approach would be the Arity and Allstate research that estimated the cost of distracted driving for the insurance industry at $9 billion. This insight was derived from data sourced from national smart phone usage, vehicle telematics and incident claims data.

See also: Distracted Driving: a Job for Insurtech?  

At Arity, our mission is to make transportation smarter, safer and more useful for everyone, and understanding and eliminating distracted driving is central to why the company was founded. What’s important is that we don’t see this solely as a technical problem. Aside from understanding the true behaviors that are causing insurance loss, we must also provide a meaningful experience to the driver to eliminate the behavior. It’s important that we don’t stop learning and experimenting; there’s so much more we can do to #enddistracteddriving.

Telematics: Moving Out of the Dark Ages?

While the number of usage-based insurance (UBI) policies reached 14 million at the end of September 2016, most insurance companies are still overwhelmed by the challenge of using collected data to rate their customers’ driving habits.

This conclusion is based on analyzing the world’s 27 largest UBI programs, including those of Admiral, Allianz, Allstate, AXA, Generali, Desjardins, Direct Line, State Farm, the Hartford, Unipol, Uniqa and Zurich.

See also: Why Exactly Does Big Data Matter?  

Progressive, the No. 1 telematics insurer globally, still uses a temporary device and does not collect GPS data. Unipol, the No. 2 player, still only collects mileage data from its customers.

We believe, however, that the prehistoric age of connected insurance analytics is ending. The era was based on the premise that all policyholders are reluctant to be “tracked.” But with most of us giving daily credit card, fingerprint, driving speed or location details to companies such as Apple, BMW or Vodafone, how to make sense of the self-censorship that insurers apply to their programs?

The truth is that more data benefits insurance companies… and the careful drivers! At the center of this change is advanced data analytics – the ability to extract insights from real-time data sources and discover risk-predictive patterns.

Our analysis, detailed in the Connected Insurance Analytics report, shows that the glaciation period’s ice is melting and that all the key insurers are now moving.

See also: Data Science: Methods Matter (Part 3)  

Progressive started a vast recruitment plan to attract data scientists. Generali also made a strong move by acquiring MyDrive, an analytics provider with early footsteps in smartphone UBI. Allstate just created Arity, which will collect data on drivers and sell analytics products to third parties. Simultaneously, Unipol created Alpha, a self-standing analytics and telematics operation.

The bulk of insurance companies is yet to act. To help them adapt to this new climate, Ptolemus published the Connected Insurance Analytics (CIA) report as a step-by-step guide to advanced analytics. It describes, analyzes and illustrates the process by which advanced analytics companies take raw driving data and transform it into real-time, individual risk profiles.

Screen Shot 2016-12-06 at 9.42.20 PM

The investigation shows that acceleration, braking and mileage are the most used — unsurprisingly — but also that the range of factors is much wider and illustrates the complexity involved in selecting the correct criteria.

To offer a predictive driving score, the report demonstrates that insurers must gain a deep understanding of driving conditions. Adding contextual data, such as road type or relative speed, is a necessary step to price customers fairly.

The full article from which this is extracted is available here.

Lessons From New Telematics Firm

The insurance industry has been abuzz with the announcement by Allstate CEO Tom Wilson that he has created a stand-alone business unit with the express purpose of monetizing telematics data that the firm has been collecting for at least the last six years.

The new company, called Arity, will provide data and analytics products to the insurer’s brands, as well as to third parties.

This is not a surprising move for Allstate.

I have been watching Allstate for the last couple of years. They have had an active research and development department. You can be assured other insurance companies are exploring similar options that will help them increase revenue in arenas beyond insurance policies..

Allstate has provided hints of its intentions for the last couple of years. In the 2015 SEC 10-K filing, the insurance company — for the first time — identified how changing technology is increasing the risk of its ability to continue to generate revenue from insurance products. Specifically, the company said:

“We are also investing in telematics and broadening the value proposition for the connected consumer. If we are not effective in anticipating the impact on our business of changing technology, including automotive technology, our ability to successfully operate may be impaired. Also, telematics devices used have been identified as a potential means for an unauthorized person to connect with a vehicle’s computer system resulting in theft or damage, which could affect our ability to successfully use these technologies.

Other potential technological changes, such as driverless cars or technologies that facilitate ride or home sharing, could disrupt the demand for our products from current customers, create coverage issues or [affect] the frequency or severity of losses, and we may not be able to respond effectively.”

Allstate identified the new risk it faced. In response, the company has been aggressively researching, developing and testing new ideas for how to use the data collected to create new types of insurance policy coverages and rating models.

See also: 6 Key Ways to Drive Innovation  

Innovation Encouraged

The company was granted 28 patents in 2015. So far in 2016, it has been awarded 15 patents. The company has also submitted 16 patent applications. Following is a small sampling of the patents:

Insurance System Related to a Vehicle to Vehicle Communication System(#9,390,451) – System and methods are disclosed for determining, through vehicle-to-vehicle communication, whether vehicles are involved in autonomous droning. Vehicle driving data and other information may be used to calculate a autonomous droning reward amount. In addition, vehicle involved in a drafting relationship in addition to, or apart from, an autonomous droning relationship may be financially rewarded. Moreover, aspects of the disclosure related to determining ruminative rewards and/or aspects of vehicle insurance procurement/underwriting.

Motor Vehicle Operating Data Collection and Analysis (#9,189,895) — A method and apparatus for collecting and evaluating powered vehicle operation utilizing on-board diagnostic components and location determining components or systems. The invention creates one or more databases whereby identifiable behavior or evaluative characteristics can be analyzed or categorized. The evaluation can include predicting likely future events. The database can be correlated or evaluated with other databases for a wide variety of uses.

Route Risk Mitigation (Utility Patent Application (A1)) – A method is disclosed for mitigating the risks associated with driving by assigning risk values to road segments and using those risk values to select less risky travel routes. Various approaches to helping users mitigate risk are presented. A computing device is configured to generate a database of risk values. That device may receive accident information, geographic information, vehicle information, and other information from one or more data sources and calculate a risk value for the associated road segment. Subsequently, the computing device may provide the associated risk value to other devices. Furthermore, a personal navigation device may receive travel route information and use that information to retrieve risk values for the road segments in the travel route. An insurance company may use this information to determine whether to adjust a quote or premium of an insurance policy. This and other aspects relating to using geographically encoded information to promote and reward risk mitigation are disclosed.

Data is king

Allstate has been granted about 43 patents in the last 18 months. A high percentage are related to data, telematics and how to use the data collected to more effectively understand driving behavior. Data and more specifically data analytics is rapidly becoming the key to unlocking new revenue sources. Data is king.

Allstate CEO Wilson was quoted in the Chicago Daily Herald saying that Arity can “incorporate new data sources and enhance analytical capabilities in ways that we weren’t able to do when it was embedded in the insurance company. It’s a big enough platform today with the Allstate customers in it, and that will continue to grow, but we’d like it to grow even faster with a broader set of customers.”

See also: Data Science: Methods Matter (Part 4)  

One option for bringing innovation to a conservative company is to spin off the innovations into a separate company. It appears that the telematics business unit just simply couldn’t operate effectively within the confines of a highly regulated and conservative company.

“The biggest risk is not taking any risk… In a world that is changing really quickly, the only strategy that is guaranteed to fail is not taking risks.” ― Mark Zuckerberg

Lessons to be Learned?

So what are the lessons to be learned?

  • Invest in research and development – finding new ways to enhance the customer experience and at the same time generate additional revenue will be key to being prepared for the uncertainty ahead.
  • Define “successful failures” — you can be assured that not everything the Allstate staff tried worked. The key to innovation is being able to learn from your failures. This is particularly challenging in a larger company where risk-taking is punished.
  • Embrace the changing nature of risk – Risk management departments are told to reduce a company’s exposure to all types of risk. To be able to respond to the rapidly changing nature of risk, you will need to increase your exposure to risk.
  • Embrace the risk dilemma –  How do you encourage innovation (taking risks) without putting the company in jeopardy? Every type of organization faces this dilemma.

What do you think? What other lessons can be learned? Is this a smart move by Allstate, or risky adventure? Leave a comment below.

This article was originally published on LinkedIn. It is reprinted with permission of Steve Anderson.