While it is in the interests of both insurers and honest policyholders to crack down on soft fraud, it is important that this sensitive issue is managed tactfully. It's prohibitively expensive for insurers to fully investigate every single claim, especially when the value is low. Moreover, efforts to detect and prevent soft fraud, which slow down claims processing, may have the unintended consequence of frustrating honest claimants, which in turn can be detrimental to retention levels. Thankfully, fraud detection systems are becoming increasingly sophisticated and insurers can now apply a range of measures to find a solution.

Detecting soft fraud

In its report, the “State of Insurance Fraud Technology,” Cary, N.C.-based analytics software developer SAS reported that 81% of respondents used automated systems employing business rules to detect fraud. Perhaps claims with a value above a certain threshold are flagged, or claims that are not supported by a police report. Rules-based systems have the benefit of being simple to apply. However, they generate a large number of false positives and may not be well suited to dealing with soft fraud. Profiling policyholders according to criteria such as credit rating or other personal risk factors alone is not going to alert an adjuster to claims padding.

Anomaly detection — applied by 45% of SAS respondents — can be used effectively for spotting soft fraud. How likely is it that a policyholder living in an apartment in a high density residential area owns a high-powered leaf blower? Is it likely that a 20-year-old driver on an average income would be driving an expensive sports car? Key performance indicators can be used to set thresholds, which if breached, will trigger an alert.

Comparing the repair or replacement cost of an item to its average retail value can also immediately flag possible claims padding. For example, a claim for $800 relating to a TV with a retail value of $400 should immediately be flagged for further investigation. Formal special investigation unit investigations can be expensive, so be cautious here. Alerts alone help reduce fraud by allowing claims managers to quickly follow up on specific areas of the claim.

Adopting predictive analytics

Predictive analytics solutions were employed by 43% of SAS respondents. With a wealth of information available to insurers about past claims, it becomes possible to develop a model of future claims. What is the average cost of a burglary claim in a geographical area? What is the average value of electronic equipment owned by a family of a certain size in a certain income bracket? In addition to being more efficient than standalone rules-based systems, predictive analytics can yield fewer false positives and can be adapted in real time to incorporate new data.

The Coalition Against Insurance Fraud has noted that around half of insurers cite a lack of IT resources as the main stumbling block in implementing anti-fraud technology. As a new generation of anti-fraud solutions are brought to the forefront, more and more insurers will see a positive return on investment as they adopt powerful analytical tools to combat soft fraud. The potential gains are substantial. Increasing the detection of soft fraud will not only reduce costs, it may even act as a deterrent for what is, after all, an opportunistic crime.

Joseph Bracken is vice president of product management for Needham, Mass.-based contents claims management software company Enservio.