Data mining is a cash crop

Agriculture Department officials were alerted to more than $250 million in fraudulent crop insurance claims in the past three years after they began using data mining. Based on that initial success, officials in the USDA's Risk Management Agency are exploring additional uses of data mining for improving Federal Crop Insurance Corp. policies and procedures.

"We're trying to apply this analysis to help us make the best policy decisions," said Garland Westmoreland, director of strategic data acquisition and analysis at the agency, which administers the crop insurance program.

Since 2000, when lawmakers allocated

$20 million for a five-year study to reduce waste, fraud and abuse in the insurance program, USDA officials have documented a better than 20 to 1 return on the $13 million they have invested in data mining. Data mining, or predictive analytics, is a statistical database technique that is useful for discovering anomalies that can be indicative of fraud.

For their data-mining studies, USDA officials use the services of experts at Tarleton State University's Center for Agribusiness Excellence. "While data-mining software has become more usable, it's still not as simple as [a Microsoft Corp.] Excel spreadsheet," said Lou Agosta, a principal analyst at Forrester Research Inc.

The USDA's risk management experts began their data-mining efforts in 2000. "We asked the person who works with our field folks to come up with a number of scenarios and then to reduce those to mathematical algorithms," Westmoreland said. The algorithms could spot policyholders who reported highly unusual crop losses.

"We were able to demonstrate rather quickly that, with data mining applied to a merged database, we could find things that could not be found any other way," said Alan Friedman, president and chief executive officer of Planning Systems Inc., which makes the data-mining software used in the studies.

Westmoreland said unusual findings prove nothing, so USDA officials typically investigate abnormalities by sending letters to farmers who report unusual crop losses. The letter states that a field inspector will visit the farm, and that usually prompts wrongdoers to drop any fraudulent claims for that year and subsequent years, Westmoreland said.

In the past few years, agency officials paid about $3 billion a year for legitimate crop loss claims, Westmoreland said. But data mining has shown that about 1,800 out of 1.5 million people enrolled in the crop insurance program attempt to file fraudulent claims.

Before officials discovered data mining, the USDA typically lost about $7 million a year from fraudulent claims. Officials tried to recover the money, but litigation is difficult and time-consuming, Westmoreland said.

"We would rather people make sure they file a valid claim and get paid for a valid claim than try to rectify claims that may have been invalid," he said. "It just works out better for everyone involved."