Fraud fighting with SAS Analytics

Fraud fighting with SAS Analytics: Fraud is zapping corporate profits and padding the cost of goods for both businesses and consumers. For organizations scrambling to detect and prevent fraud, advanced data analytics are vital to quickly finding bad transactions within big data. For CNA, the eighth largest US commercial insurer, fighting fraud is fundamental. "We train our adjusters to identify red flags, but we knew we could do a better job identifying likely fraud and also avoid the wasted expense of investigating false positives,” said Tim Wolfe, Assistant Vice President of CNA's Special Investigations Unit. Armed with SAS predictive models, the company runs weekly analyses against its claims data and text notes from adjusters. “Each Monday morning, after a weekend data run, SAS flags a percentage of claim alerts that score high for fraud potential. We review about 100 alerts a week, and we're averaging a 20 percent hit rate – about one in five alerts that we review is a good case for investigation.”

Industry research suggests that 10 percent of claims likely contain a fraudulent element. Before, CNA was only flagging 3.7 percent as potentially fraudulent. Within two years of implementing SAS, CNA saw that rise to 8.1 percent, resulting in recovered or prevented fraudulent claims totaling over $6.4 million.

In 2013, the IRS paid out $5.8 billion in tax refunds it later realized were fraudulent. Such tax scams are one reason the Kentucky Department of Revenue (KDOR) is stepping up efforts to detect individual income tax compliance issues and save taxpayer money. KDOR’s weapon of choice is SAS predictive analytics.

“Our job is not just to collect taxes, but to get taxpayers the money they are owed as quickly as possible,” said Mack Gillim, Executive Director of the Office of Processing and Enforcement for KDOR. “Increasing fraud and abuse puts even greater responsibility on us to be diligent. Analytics helps with that.”

Tax returns are now scored every night, with potential issues flagged for examiners to review the following day. This quick process helps KDOR in its aim to send refund checks to taxpayers within 14 days. Working in parallel with the existing system during this year's tax season, SAS also helped stop an additional $1 million in fraud in the early months of 2015. KDOR expects the year-end total to double that amount.

As the world’s most widely used advanced analytics platform, SAS has been on the frontline of the fraud battle for more than 30 years,” said Stu Bradley, Senior Director of Fraud and Security Solutions at SAS. “SAS products target concerns across fraud and improper payments, anti-money laundering compliance, and cybersecurity, helping our customers impact their bottom line.

You may also like to read, Predictive Analytics Free Software, Top Predictive Analytics Software, Predictive Analytics Software API, Top Free Data Mining Software, Top Data Mining Software,and Data Ingestion Tools.

Top Predictive Lead Scoring Software, Top Artificial Intelligence Platforms, Top Predictive Pricing Platforms,and Top Artificial Neural Network Software, and Customer Churn, Renew, Upsell, Cross Sell Software Tools

More Information on Predictive Analysis Process

Predictive Analytics Process Flow

For more information of predictive analytics process, please review the overview of each components in the predictive analytics process: data collection (data mining), data analysis, statistical analysis, predictive modeling and predictive model deployment.