Insurers still struggle with predictive analytics: Study

LAS VEGAS — The use of anti-fraud technology by insurers in North America is on the rise. However, many companies are still struggling with the deployment of proactive predictive analytics tools because of resource constraints, according to a study.

Nearly 95 per cent of insurance companies reported using anti-fraud software as of 2013. That’s a marked increase from just 88 per cent the previous year, according to a study conducted by the Coalition Against Insurance Fraud with the help of big data analytics software maker SAS Institute. The CAIF, is a Washington, D.C.-based alliance of insurance companies, government agencies and consumer groups that have banded together in 1993 to battle insurance fraud through legislative advocacy and consumer education.

The organization’s latest survey — released here as part of SAS’ Leadership conference — also found that insurance companies tend to focus the use of technology against claims-based fraud and only less than half of the businesses are using technology to combat underwriting and internal fraud, which the CAIF said are emerging concerns in the industry.

Majority of the insurers (53 per cent) cited lack of IT resources as their biggest challenge in implementing anti-fraud technology.

The CAIF study is a follow-up to a 2012 survey conducted by the organization to understand how the industry is deploying technology to tackle insurance crimes. The study involved a qualitative research including a series of in-depth interviews with experts and senior insurance executives as well as an online survey of 42 insurers, which CAIF said represented a significant share of the property and casualty insurance market.

In past years, most schemes focused on false auto thefts and property arson, the report said. However, fraudsters have shifted their focus to “bodily injuries and suspicious activities by medical providers.”

“Workers compensation and auto insurance most notably have seen these changes in tactics,” the report said. “In response, insurers are increasingly adopting advance analytics to counter the changing nature of fraudulent activity.”

Another rising source of fraud is point-of-sale or underwriting where fraudsters conspire to reduce insurance premiums.

“Fraudsters can test system thresholds by filling many different applications online and by manipulating rates by changing rating factors to reduce premiums,” the report said. “In addition, analysis suggests that a significant amount of claims fraud is perpetuated through illegally obtained policies.”

The number of insurance companies reporting cyber-attacks meant to steal large amounts of customer personal information has risen significantly since 2012, the CAIF report said. Yet, only 14 per cent of companies employ technology to prevent cyber-attacks.

The traditional and “first line of defence” that most insurance companies deploy is automated red flags/business rules systems, according to the study. A total of 81 per cent of respondents reported using such technologies.

The advantage of business rules-based systems is simplicity.

“Unfortunately, however, business rules often generate high false-positive rates and undetected fraud because fraudsters can easily learn and manipulate such rules,” CAIF said.

Seventeen per cent of respondents cited excessive false-positives/negatives as the biggest challenges to implementing an anti-fraud solution.

Lack of IT resources also forces many companies to lean on already-overworked IT departments. Data integration and poor data quality (14 per cent), lack of return of investment (eight per cent), inability of special investigation units to handle volume of potential fraudulent claims (six per cent) and delayed adjudication (three per cent) were other challenges cited.

Interestingly, in the 2012 survey, the percentage of respondents that cited ROI as a challenge was 36 per cent.

“Insurers are investing in different technologies to combat fraud, but a common component to all these solutions is data,” said Stuart Rose, global insurance marketing principal at SAS. “The ability to aggregate and easily visualize data is essential to identify specific fraud patterns.”

Other technologies deployed by insurance companies were:

-Link analysis (50 per cent)

-Anomaly detection (45 per cent)

-Predictive modeling (43 per cent)

-Text mining (43 per cent)

-Data visualization (40 per cent)

“Technology is playing a larger and more trusted role with insurers in countering growing fraud threats,” said Dennis Jay, the coalition’s executive director, in a statement. “Software tools provide the efficiency insurers need to thwart more scams and impose downward pressure on premiums for policy holders.”

The study said employing the “right mix of tool and technologies” will result in a higher fraud-detection rate.

Would you recommend this article?


Thanks for taking the time to let us know what you think of this article!
We'd love to hear your opinion about this or any other story you read in our publication.

Jim Love, Chief Content Officer, IT World Canada

Featured Download

Nestor E. Arellano
Nestor E. Arellano
Toronto-based journalist specializing in technology and business news. Blogs and tweets on the latest tech trends and gadgets.

Featured Articles

Cybersecurity in 2024: Priorities and challenges for Canadian organizations 

By Derek Manky As predictions for 2024 point to the continued expansion...

Survey shows generative AI is a top priority for Canadian corporate leaders.

Leaders are devoting significant budget to generative AI for 2024 Canadian corporate...

Related Tech News

Tech Jobs

Our experienced team of journalists and bloggers bring you engaging in-depth interviews, videos and content targeted to IT professionals and line-of-business executives.

Tech Companies Hiring Right Now