White paper – technical report
Using data mining
to detect fraud
U s i n g d a t a m i n i n g t o d e t e c t f r a u d
Every government agency that exchanges money with citizens, service providers or
vendors risks exposure to fraud and abuse.
Agencies around the world lose more and more money through fraud every year. They
need to recoup this lost money so they can continue providing superior services for their
citizens. These agencies can identify fraudulent activity by mining their existing data.
Typically, agency auditors use past experience and intuition to create profiles describing
fraudulently filed claims. But these unproven theories waste time and miss opportunities
as auditors unknowingly review legitimate claims while failing to catch fraudulent ones.
To ensure auditors target claims that have the greatest likelihood of adjustment, many
social service agencies have incorporated data mining into their investigating and audit-
ing processes. Data mining combines powerful analytical techniques with your business
knowledge to turn data you’ve already acquired into the insight you need to identify
probable instances of fraud and abuse.
Discover how to recoup more money
How does your agency determine which of its thousands or millions of claims are legitimate?
Perhaps, your auditors rely on hunches and intuition to determine which claims or payment
requests might be fraudulent. Do these less-than-precise methods cause your auditors to
waste time reviewing claims or payments that have little or no chance of being recouped? Or
maybe your auditors tend to target claims or payment requests that represent inconsequen-
tial adjustments, while missing the ones that offer significant amounts of money to recoup.
With data mining, your auditors can focus on recovering money so much-needed programs
receive the funds required to effectively serve citizens.
What if you could:
■ Isolate the factors that indicate a claim or payment request has a high probability
■ Develop rules and use them to