New Study Shows Insurance Fraud Detection Technology use on the Rise
September 13, 2012
By Frank Griffin
TMCnet Contributing Writer
The cost of insurance fraud adds to the premium of every policy holder to the tune of hundreds of millions of dollars every year. To overcome this problem insurance companies have been trying to implement sophisticated computer software designed to detect fraud in the early stages of a claim. Catching fraudulent claims early is very important because it is estimated only 20 percent of all fraudulent claims are detected or denied. Once a claim is paid, the chance of recovery is low or non -existent.
The study by the Coalition Against Insurance Fraud sponsored by SAS (News - Alert) is intended to understand how technology is used and applied in detecting and preventing fraudulent claims.
The technological tools used to detect fraud are extremely dependent on the amount and quality of the data used for the analysis of a claim. The information used for this analysis is often outdated part of legacy systems with external databases. According to the survey, most of the respondents used a variety of sources with their own carrier claims history data at 69 percent, followed by 62 percent using public records, and watch lists or fraud alerts from the industry at 57 percent.
The study continues to point out one of the biggest obstacles to using the information is it is not structured. Only 25 percent of the information is organized for proper usage leaving 75 percent of the data practically unusable or too difficult to use and therefore not applied by investigators or insurance agents.
“It’s really about putting the data together so that it makes sense to an investigator who has a large pending folder. It is triage, it is prioritization and it is allocation of resources, using data to inform those decisions,” said Frank Llende, senior manager at Allstate,
The technology used to catch a potential fraudulent claim is a system designed with a ruled based system which scores each claim against a base line or predefined set. If the score goes above a certain threshold it will set an alert to the SIU (Special Investigation Units) members and they will investigate the validity of the alarm. The problem with this system is it causes many false positives wasting investigative man hours and resources. The false positives also enable the criminals to learn what sets alarms and they find ways to circumvent detection.
Donald Light, a senior analyst at Celent said in his report, “Insurance Fraud Mitigation Technology,” “That the success of fraud detection is the systematic detection of suspicious activity using a combination of analytical techniques (business rules, predictive modeling, anomaly detection and network analysis) to determine the likelihood of claims fraud.”
The goal of the study was to determine to what extent insurers use anti-fraud technology. The survey shows the willingness of insurance agents and insurers to use the technology to lower and eliminate fraudulent claims. The problem is the system in place is not organized and structured to disseminate the best and latest available information at the time.
Want to learn more about the latest in communications and technology? Then be sure to attend ITEXPO West 2012, taking place Oct. 2-5, in Austin, TX. Stay in touch with everything happening at ITEXPO (News - Alert). Follow us on Twitter.
Edited by Brooke Neuman
Article comments powered by
|