Insurance carriers using telematics to assess the risk of auto policyholders could accumulate up to 15 megabytes of data per year per customer and will be therefore be unable to rely on traditional data mining technology, suggests business intelligence software maker SAS Institute Inc.
In a recently-published white paper, Cary, N.C.-based SAS recommended that carriers using telematics implement an enterprise data management strategy.
“Due to the sheer size of telematics data, insurers must consider a distributed, in-memory environment to display the results of data exploration and analysis that is meaningful but not overwhelming.”
The white paper, titled Telematics: How Big Data is Transforming the Auto Insurance Industry, includes content from Stuart Rose, SAS Institute’s global insurance marketing director. It forecasts that by 2020, more than 20% of premiums in the U.S. auto market will be generated by telematics devices, which record data such as milage, data, time, location, speed, cornering, harsh braking and frequent lane changing.
A telematics device will produce a data record every second with information such as the force of acceleration (measured in Gs), milage and fuel consumption, according to the white paper. A carrier with a customer base of 100,000 could generate more than a terabyte, or a trillion bytes, of data per year. Among other things, SAS Institute’s software is designed to let users query and generate reports from computer databases.
In its white paper, SAS Insitute says auto insurance providers writers using telematics should have a data management strategy, which should include data integration to improve the flow of information. It should also manage access to the data and create a single, accurate view of all telematics data.