False claims cost insurance companies approximately USD 34 Billion every year. Home and auto insurance fraud top the list. No wonder more and more companies are investing in anti-fraud technology in which big data analytics plays the lead catalyst’s role.

But how is big data holding up against traditional fraud detection techniques? A WNS survey on the fraud detection techniques used by Property and Casualty insurers in the U.S. confirms that big data analytics trumps traditional methods in detecting fraud.

According to the survey, insurers using big data analytics in the claims cycle reported higher benefits such as 40 percent improvement in the average referral time and 50 percent more average referrals.

Insurers who deployed big data analytics in the investigation stage noticed their average claim investigation cost come down by a staggering 67 percent. The average investigation time for each claim had shortened considerably as compared to insurers who were using traditional methods. In the investigation stage, all insurers who had deployed big data witnessed a reduction in the false-positive and false-negative rates. They also saw a higher number of investigations per investigator.

With big data analytics, companies can calibrate and test their approaches continuously instead of relying on an established model. It gives insurers the flexibility to apply effective models as the situation demands to unravel fraudulent activities.

If big data has such an impact in the claims cycle, what would be the business outcome if it is deployed across the policy life cycle? Connect with the author here.

To know more, visit at WNS DecisionPointTM | Insurance Fraud Detection and Prevention in the Era of Big Data

Join the conversation