Analytics and the Telematics Information Overload

By Stuart Rose, Global Insurance Marketing Director, SAS

Telematics is set to revolutionize the insurance industry, making it possible to develop more accurate pricing, improve risk management and better assess claims and therefore reduce losses. But is the industry prepared for it?

Since it first launched in 1998 by Progressive Insurance in the US, telematics technology has evolved significantly. In 2012, Progressive reported that it wrote over $1 billion in premium revenue for usage-based insurance policies, and by 2020 it is forecasted that more than 25 per cent of the US and Canadian auto insurance premium revenue will be generated via telematics, representing over $30 billion.

Insurers looking to adopt telematics will face three main data-related challenges: how to manage the huge amount of data created by the technology; how to extract value from the data, and how to turn data into KPIs and real-time pricing models.

Challenge 1: Data Overload

First let’s look at the data deluge facing the insurance industry with the adoption of telematics. Telematics devices create a data record every second, which includes such information as date, time, speed, longitude, latitude, acceleration or deceleration (g-force), cumulative mileage and fuel consumption of the vehicle. From a data persective, these records or data sets can represent approximately 5 to 15 megabytes of data, per customer, per year depending on the frequency and length of insured trips. With a customer base of just 100,000 vehicles that adds up to more than 1 terabyte of data per year!

Not only is there a huge amount of data associated with telematics, but the many different types of telematics devices also result in a wide variety of different data formats. This results in increased challenges such as cost, data quality issues from missing data, and complexity of bringing all the sources together for processing.

What can be done to overcome the overload? Insurers need to implement an enterprise-wide data management strategy. The strategy should provide a unified environment of solutions, tools and methodologies and workflows for managing the telematics data as a core asset. It consists of four key components:

  • Data integration: Improve the flow of accurate telematics information across the organization
  • Data quality: Ensure information integrity and excellence by managing the data quality life cycle
  • Enterprise data access: Manage the access and use of data across the enterprise
  • Master data management: Create a single, accurate and unified view of all the telematics data

Additionally, the data management strategy must be flexible and scalable to reduce the time and effort required to filter, aggregate and structure the exponential growth in telematics data.

Challenge 2: Turning information into insight

Data from telematics can help solve questions such as ‘which driver is more dangerous, one that drives 5,000 kilometres annually on inner-city roads, or one that travels more than 20,000 kilometres on highways?’ But with mountains of information available from telematics, how do insurers determine which variables are predictive or forecast driving behavior, claims experience and more?

In order to realize the revolutionary potential of telematics, insurance companies should use data exploration and analytics to mine the vast amount of data available then rank and weigh the hundreds of new variables generated. For example, insurers could use a correlation matrix to quickly identify which variables are related and the strength of the relationship.

But with all this new data created by telematics traditional data mining technology isn’t powerful enough. Instead, look for solutions that incorporate a distributed, in-memory environment to display results of data exploration and analysis in a way that is meaningful and not overwhelming. Powerful in-memory computing or high performance analytics enable companies to prepare, explore and model multiple scenarios using data volumes, which could not be handled by older technologies, to deliver accurate and rapid insights. Analyzing and processing telematics data that may have taken days or hours is reduced to minutes or seconds, leaving time for companies to ask more ‘what if’ questions; developing models that can be quickly adjusted and run again.

Challenge 3: The key to real-time pricing and risk reduction

Auto insurance is a highly competitive industry and profitability is often eroded by pricing not tightly aligned with individual risk. Much of the benefit of telematics lies in it equipping insurers with the ability to present information on the customer’s specific driving behaviour and incent them to drive more safely. For instance, UK insurer, Young Marmalade, sends email alerts to the driver when risk rises.

Pricing models also stand to be improved through telematics as it provides insurers the ability to use real-time data for real-time pricing and charge customers based on a monthly usage basis. The transparency delivered by telematics also makes it possible for insurers to reduce rate evasion or ‘premium leakage’ caused by customers misrepresenting information (either deliberately or not.) This is estimated to amount to 10 per cent of premium revenue.

However, generating personalized pricing and risk reduction is not simple. Not only does use of telematics result in massive amounts of data, but the speed (or velocity) at which this data arrives is challenging. With high performance analytics insurers can access and process varying velocities of data quickly. Insurance companies should consider a “stream it, score it, store it” approach. This enables analytics to be applied on the front end to separate the meaningful telematics data from the unimportant data or “the noise”.

Moving forward with telematics

In an industry such as insurance that can often be slow to adopt new innovations, telematics may seem too complex to undertake. While telematics has the power to transform how insurers in Canada and around the world operate, and early adopters have the potential to realize massive competitive advantage, as with many innovations, realizing the benefits may not be straightforward. Vital to the success of these programs is the collection, storing and analyzing of telematics data. As telematics is still in its infancy in Canada, insurers still have time to evaluate their needs and implement the technologies that will help them stay competitive.

About the Author

Stuart Rose is global insurance marketing director at Cary, N.C.-based SAS. Rose, a 25-year veteran of the insurance industry, began his career as an actuary. He has worked for a global insurance carrier in both its life and property divisions and has worked for several software vendors, where he was responsible for marketing, product management, and application development.

Stuart is a regular contributor to insurance publications and the Analytic Insurer blog. He frequently speaks at insurance conferences and is co-author of the book Executive Guide to Solvency II.

About SAS

SAS is the leader in business analytics software and services, and the largest independent vendor in the business intelligence market. Through innovative solutions, SAS helps customers at more than 60,000 sites improve performance and deliver value by making better decisions faster. Since 1976 SAS has been giving customers around the world The Power to Know®.

Source: SAS