Predictive analysis of social networks

SAS has introduced a Social Network Analysis solution that helps institutions detect and prevent fraud by going beyond individual and account views to analyze all related activities and relationships at a network dimension.

SAS Social Network Analysis, new software featured in the SAS Fraud framework, helps investigators detect and prevent fraud by going beyond transaction and customer views to analyze 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 unique network visualization 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 visualizations of relationships that include individuals flagged by existing rules, anomaly detection or predictive modeling. 

"With SAS Social Network Analysis, it is possible to find previously unknown relationships that by themselves seem innocuous, but in concert are clearly fraudulent," said Dr. John Brocklebank, Vice President of 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."