Prev
CARY, N.C.--(BUSINESS WIRE)--SAS, leader in business analytics software and services, recently received patent approval for "Computer-Implemented Predictive Model Generation Systems and Methods"
(
US patent 7,788,195 B1) related to technology at the heart of
SAS® Fraud Management
, an integral component of the SAS Enterprise Financial Crimes Framework for Banking. SAS Fraud Management employs a "Self-Organizing Neural Network Arboretum" (SONNA) modeling capability to build its unique hybrid approach to consortium and custom models.
SAS Fraud Management offers significant improvement in fraud detection performance compared to the performance of regular, non-linear modeling techniques like neural networks. A "score-on-demand" process helps card issuers obtain updated scores based upon the passage of time. The SAS solution provides the creation of risk-based reason factor groups, giving an organization's fraud operations and analytics groups more insight and context to the risks and reasons behind the model score - optimizing responses and automating actions to a high-scoring transaction.
United States Patent 7,788,195 Abstract
Systems and methods for performing fraud detection. As an example, a system and method can be configured to build a set of predictive models to predict credit card or debit card fraud. A first predictive model is trained using a set of training data. A partitioning criterion is used to determine how to partition the training data into partitions. Another predictive model is trained using at least one of the partitions of training data in order to generate a second predictive model. The predictive models are combined for use in predicting credit card or debit card fraud.
Read more.