SAS Fraud Framework Incorporated With Alert Management Guards Transactions

New SAS Fraud Framework from SAS effectively fights fraud enabling organizations continually improve the monitoring of customer behavior across multiple accounts and systems. This framework includes components that support detection and alert generation, alert management and case management, and includes

By None

New SAS Fraud Framework from SAS effectively fights fraud enabling organizations continually improve the monitoring of customer behavior across multiple accounts and systems.

This framework includes components that support detection and alert generation, alert management and case management, and includes the new SAS Social Network Analysis tool. Industry-specific business rules, models and other capabilities will help banking, insurance and government organisations to prevent and detect various types of fraudulent activities and manage efforts against them.

Designed to help detect and prevent both line-of-business fraud and cross-channel enterprise fraud, organisations can use the framework to help increase fraud detection rates, reduce false positives and streamline investigative resources.

At the core of the framework is a profiling engine that scores individuals, accounts, products and networks based on rules, fraud scores and links to known fraudsters. An enterprise view of fraud exposure and risk is provided by consolidating alerts from multiple systems.

SAS Social Network Analysis, new software featured in the framework, helps investigators detect and prevent fraud by going beyond transaction and customer views to analyse all related activities and relationships within a network, such as shared address, telephone numbers, employment, account ownership and other key transactional data.

SAS Social Network Analysis provides an interface that enables fast access to full customer details and all related parties and networks, resulting in quicker case assessments and better dossier production.

The network visualisation interface helps investigators actually see network connections more clearly so they can uncover previously unknown relationships and conduct more effective and efficient investigations. In addition to detection and risk scoring, investigation teams can review visualisations of relationships that include individuals flagged by existing rules, anomaly detection or predictive modeling.

“In our research of the drivers, strategies and technologies for the global banking industry in 2009, we see analytics to manage fraud and other risk as a prioritised technology initiative for organisations to address the global economic climate,” says Jim Eckenrode, research executive, Banking & Payments, TowerGroup. “With the combined elements of increased regulation and rapidly evolving, cross-channel fraud, we project that banks will need to invest in broader, more firm wide fraud and risk solutions.”

Health Care Service Corporation (HCSC) has been using SAS Enterprise Miner for data mining and analytics within its anti-fraud program for years.

We mine years and terabytes of data relating to claims, providers, members, groups, accounts and products from all four of our Blue Cross and Blue Shield plans, says Kyle Cheek, director, Enterprise Informatics, HCSC. Our integrated platform, which includes SAS, helps us to succeed in proactively identifying fraud. Were always looking for more inventive and effective ways to fight fraud.

With SAS Social Network Analysis, it is possible to find previously unknown relationships that by themselves seem innocuous, but in concert are clearly fraudulent, says Dr. John Brocklebank, vice president, SAS Solutions OnDemand.

In addition, the software has many uses beyond fraud detection and prevention. Businesses such as telecommunications companies and banks can use network analysis to better understand customer behavior and target relevant offerings to new and existing customers. The ability to differentiate between influencers and followers helps to generate revenue and build customer loyalty.

L.D.

«