Fraudulent crime is growing more and more complex, and current fraud detection techniques are outdated and unsatisfactory. Insurers must rethink their existing fraud detection processes or risk losing profitability. Currently, Insurers analyze a mere 15-20% of all data available within their organization and mostly focus on that which is already in a structured form. This results in significant amounts of fraudulent claims going undetected, eroding insurers’ revenue by ~10% every year.
By analyzing data from within the insurance organization (such as log notes and adjuster’s notes) as well as from external sources (such as social media interactions of policy holders), collectively referred to as Big Data, insurers could unearth complex, unseen fraud patterns and boost their detection rate. With fewer fraudulent claims being paid out, insurers would be able to offer more competitive premiums and operate at a higher level of profitability.
In order to assess the awareness, perceived benefits and challenges of Big Data analytics, WNS DecisionPoint(TM) conducted a study of select U.S. insurers who cater to personal lines, commercial lines and combined lines of insurance. The study results provide insights into the means taken by insurers to effectively capture, store, aggregate, and analyze Big data to combat fraud at all stages of the policy lifecycle thereby:
- Reducing referral time and gaining more referrals
- Reducing investigation time and cost
- Understanding referrals better
- Reducing false-positive and false-negative rates
- Achieving a higher number of investigations per investigator
For a more thorough look at how Big Data analytics fortifies existing fraud management browse through the slideshare file or visit our site: