The Los Angeles County Department of Public Social Services (DPSS) has begun using data mining technology to identify potential fraud, enhance investigations and prevent improper payments for assistance. The technology is saving millions of dollars and improving efficiencies in the department.

DPSS offers a range of programs, including temporary financial assistance, food benefits, in-home support services for the elderly and disabled, and other financial assistance. In 2008, Los Angeles County launched a pilot project with Cary, N.C.-based SAS to identify potential fraud in the CalWORKs Stage 1 Child Care Program. Fraud cases can include participants/recipients falsifying employment to qualify for subsidized child care services, as well as fictitious child care providers colluding with participants/recipients who falsely declare that their children are attending that child care location.

The pilot achieved an 85 percent accuracy rate in detecting collusive fraud rings, which is projected to save approximately $2.2 million in new fraud referrals, approximately $1.6 million in early detection of fraud, and approximately $3 million in other efficiencies.

Building on those results, the Data Mining Solution (DMS) for Child Care Welfare Fraud Detection went live in May 2011. DPSS officials want to better prevent large fund losses by predicting which benefit recipients and service providers are most likely to engage in fraudulent activity. Using the SAS Fraud Framework for Government and SAS data mining technology with social network analysis, predictive analysis, rules management, and forecasting techniques, DPSS began identifying high-risk cases in the Child Care Program and referring them to investigators.

As a result, DPSS staff can identify and expedite the review of suspicious cases much earlier than waiting on referrals from contracted agencies or other referral sources. So far, the DMS has produced 197 additional referrals for child care fraud investigations. In addition, DPSS has detected two conspiracy groups and mapped a network of participants and providers to display their relationships. The social relationship network display shows a web of complex relations linked, for example, by common telephone numbers and addresses. In one case, DPSS staff found a child care provider serving many participants colluding in fraudulent activities. The investigation currently is being conducted on six separate conspiracy allegations that were a direct result of a data mining review by investigative staff.