Drive Safely, Drive Results:

How Insurers Use Predictive Data to Improve Pricing and Reduce Road Risks

Remember the early days of the pandemic? Cities became ghost towns, and public spaces were no longer public, as everyone locked in to avoid getting infected. COVID has affected most aspects of our lives, and mobility was no different. With work and school going remote and traveling severely limited or outright prohibited, roads emptied. As a result, traffic remained light—even though driving was the only way to get a little taste of the outside world for many.

Less traffic meant fewer accidents. A recent study based on data from the state of Louisiana reported a 47% reduction in the accident rate during the lockdown. And in April 2020, the first month of a full national lockdown in the UK, the number of accident casualties decreased by 68% compared to the 2017-2019 average.

Unfortunately, lighter traffic also had an adverse side effect. The number of accidents dropped, but empty streets encouraged drivers to engage in more risky behaviors. Worse still, though the lockdowns have eventually ended, these bad habits stuck.

One answer to this lingering carelessness is predictive data analytics. In this article, we’ll show you how DSaaS (Data Science as a Service) solutions can serve to minimize behavior-based road dangers. Then, we’ll use the insurance industry example to prove that similar methods can also help mobility-related businesses build better, personalized products and services.

What you'll learn

Predicting driver behavior, preventing road hazards

To start, let’s make one thing clear: there’s no coming back to the pandemic-era traffic intensity. Driving is a commodity most people aren’t willing to give up, so convincing them to do that isn’t a plausible option. Instead, we may tap into data to see how they drive. Then, we can work with those insights to change risky habits and prevent road accidents.

But to find the answers, you first need to know what questions to ask. Let’s learn more about the data you can use to predict and evaluate risk.

Know the risk factors

There’s much more to driving than just stepping on a pedal and turning the wheel. Drivers must pay attention to their surroundings, road conditions, weather, signs, and more. Correctly interpreting and reacting to the road environment matters just as much, and often makes the difference between safe and hazardous driving.

That’s nothing new. But since these factors are crucial to road safety, why not use them together to anticipate dangerous road situations?

To do that properly, we must consider contextual and behavioral factors.

Contextual Risk Factors

Behavioral risk factors are concerned with how drivers’ behavior affects safety on the road. Speeding, harsh braking, or swerving, for instance, are all associated with road accidents. But even when drivers follow road rules to the letter, fatigue and phone distraction can still be just as dangerous as recklessness. All that and other behavioral data can be tracked using telematics devices and should be considered alongside contextual data in risk analysis.

Context matters…

With contextual and behavioral data in place, it’s time to see what insights we can extract and how we can turn them into action.

The key to accurate predictions lies in finding patterns. When it comes to contextual data, the perfect use case is identifying accident hotspots, i.e., places where accidents occur more frequently than others due to poor road conditions, misguiding signage, or specific road characteristics (e.g., sharp curves or steep slopes). Another risk factor that occurs in patterns, depending on the hour and day of the week, is traffic intensity.

The knowledge of traffic and accident rate patterns allows drivers to avoid hotspots and roads that are often dangerously busy. This approach helps reduce the risk, especially when you factor in other risks, such as weather. For instance, if heavy rain is expected, drivers may consider choosing a different route to steer clear of a particularly unsafe, crowded motorway exit when visibility and traction are limited.

 

… but driver behavior is just as important

However, contextual factors are often out of our control and hence difficult to act on. Weather is the most glaring example, but other factors, like road conditions and infrastructure, are also difficult to manage for drivers and fleet managers. Technically, they could take a rerouting to avoid dangerous spots, but in reality, it’s not always possible or efficient.

What we can do is track how drivers react to these external circumstances and use that knowledge to change their dangerous road habits. 

Let’s get back to our example. Taking that dreaded motorway exit may be unavoidable, despite the rain and heavy traffic. But instead of just hoping for the best, behavioral data allows drivers and mobility businesses to take an active approach. We can predict how a particular driver will react to external risk factors based on historical records. 

Will they maintain high speed despite low visibility? Can they stay focused enough with so many vehicles around? Did they have any near-misses in similar road situations in the past? Knowing the answers to these questions makes risk predictions more accurate and actionable, allowing drivers to adjust their driving style accordingly.

By diving deep into data, mobility analysts can find links between various contextual and behavioral risk factors. Some conclusions can be surprising. For example, good weather conditions (daylight, low traffic) may encourage drivers to step on the gas, paradoxically increasing the likelihood of an accident. Similarly, despite a low average vehicle speed, congestion and traffic jams can be extremely conducive to crashes, largely due to how irritating they are. Combine that with a dense concentration of drivers, and you have a recipe for distraction, road rage, and tailgating.

These not-so-obvious insights prove that combining contextual and behavioral data is a powerful weapon in the fight against road hazards. But aside from increasing traffic safety, businesses can use the insights provided by DSaaS solutions to enhance their services, develop new, data-informed products, and drive profits. One industry that has successfully done that is insurance.

 

Aligning insurance pricing with road risk assessment

Traditionally, insurance providers relied on static risk factors such as vehicle characteristics (e.g., brand, model, condition), driver demographics (e.g., age, place of residence), and claims history for developing pricing models. While this used to be the industry standard, policy rates based on static data failed to reflect one crucial thing: how the car was used.

That changed when insurance providers started to adopt telematics. The ability to measure dynamic factors such as distance covered, acceleration, or location allowed insurers to take a different approach with usage-based insurance (UBI) and new pricing models.

UBI models

UBIs are a significant step forward in car insurance. Still, each of these models can use predictive analytics of the behavioral data even better to determine each driver’s risk exposure:

As you can see, these models can involve various factors. To consistently come up with reliable predictions, knowing which factors are most relevant in evaluating the risk is crucial. Some of the most important ones are

Assessing individual risk exposure isn’t easy, but it’s well worth the effort. Telematics and the predictive analysis of driver behavior offer twofold benefits for drivers and insurers.

Firstly, insurance providers no longer rely solely on claims history and other static data to calculate drivers’ risk exposure. Instead, they can actively calculate their risk score based on dynamic behavioral data to offer custom policy rates. Competitive pricing attracts new customers, especially young drivers and those who want to take advantage of their safe driving skills.

Then there’s safety. Usage-based pricing encourages responsible behavior on the road even more efficiently when data-driven predictions back it. DSaaS also enables insurers to educate drivers and provide them with practical insights for specific road situations to reduce the number of accidents.

But the above key gains aside, it’s worth noting that the combination of telematics and analytics can provide an advantage to industries beyond insurance. From public transportation authorities, through healthcare systems, to commercial fleet operators, preventing road accidents benefits numerous sectors and players. If you are wondering how applying data science technology in your field could help make roads safer and drive better business results, Motion-S experts are here to consult and assist you.

Key takeaways: Risk assessment based on contextual data can be extremely powerful; when applied correctly, besides providing revenue-improving insights, it also helps save people’s lives. Still, the technique needs to be enhanced with driver-specific behavioral data and predictive analytics to provide optimal results. 

The insurance industry has already realized the potential of that combination and uses data analytics to inform policy rating processes while limiting road hazards. Other sectors can use it to improve their results, too. Whatever the end goal they define for that journey, it always begins with taking the first step and starting the conversation

Would you like to one of our experts?

Get in touch and we'll get back to you asap!

Topics you might be interested in

Drive Safely, Drive Results: How Insurers Use Predictive Data to Improve Pricing and Reduce Road Risks

Remember the early days of the pandemic? Cities became ghost towns, and public spaces were no longer public, as everyone locked in to avoid getting infected. COVID has affected most aspects of our lives, and mobility was no different. With work and school going remote and traveling severely limited or outright prohibited, roads emptied. As a result, traffic remained light—even though driving was the only way to get a little taste of the outside world for many. … Read More

Supercharge Your EV Transition with Mobility Data Analytics

The invention of the gas-powered car by Carl Benz in 1885 wasn’t just another step in the history of mobility—this time, humanity has made a real leap forward. By making transportation more efficient and accessible, internal combustion engine (ICE) vehicles have affected all industries in one way or another. Over time, we started to rely on them so heavily that we now design our routines, lifestyles, and even entire cities around them.

But no king rules forever. Fast-forward to today, and after almost 130 years, the reign of combustion engine cars is slowly but surely coming to an end. A new contender is on the rise—electric vehicles (EVs). … Read More

Protect Your Vehicle Residual Value Using the Power of Data

According to various sources, a new car loses 9–11% of its value the moment you drive off the dealer’s lot. Over 2-3 years, its price may diminish by more than a half! Although it might seem that the situation is helpless, data science can provide a cure. Learn how applying the right algorithms on telematics data can help you protect and boost the value of your vehicles.
Read More

DSaaS (Data Science as a Service): Stepping Up the Gear with Vehicle Predictive Maintenance

Picture this. You’re driving back home after a long day of hard work. Exhausted from a series of back-to-back calls, starving despite that quick, half-eaten sandwich you rushed through between one virtual meeting and another. Dying to finally get well-deserved rest.
But just then, a sharp squeal comes from under the hood. Is it an issue with brakes or a loose or worn fan belt? Maybe the steering system went down?
Either way, your dreams of a good evening’s rest are now ruined, and you’re up for towing or an unplanned inspection. Both of which are going to cost you dearly.
Now, what if all of that time and hassle could have been avoided?
Read More

Mobility Data Analytics: For Whom, When, and Why?

Recently, we discussed the differences and similarities between data analytics and data science. Today, we’re going to investigate the first one in more detail, focusing on its use in the context of mobility. Who uses data analytics solutions, what are the core use cases, and what aspects to consider when applying analytics to mobility? Check out this introduction to our 3-part series on data analytics SaaS. … Read More

BOOK YOUR CONSULTATION NOW

We'd love to discuss with you your data science need.
Get in touch, and we'll be more than happy to help!

BOOK YOUR DEMO NOW

We'd love to show you the power of our data-driven products.
Book your personal demonstration now!

GET YOUR FREE API TRIAL NOW!

Test drive our API Suite for 30 days!
Tell us a bit about yourself, and we’ll get in touch with you in no time.