05819226 is referenced by 360 patents and cites 10 patents.

An automated system and method detects fraudulent transactions using a predictive model such as a neural network to evaluate individual customer accounts and identify potentially fraudulent transactions based on learned relationships among known variables. The system may also output reason codes indicating relative contributions of various variables to a particular result. The system periodically monitors its performance and redevelops the model when performance drops below a predetermined level.

Title
Fraud detection using predictive modeling
Application Number
7/941971
Publication Number
5819226
Application Date
September 8, 1992
Publication Date
October 6, 1998
Inventor
Allen Jost
San Diego
CA, US
Anu K Pathria
Oakland
CA, US
Michael A Lazarus
San Diego
CA, US
William M Ferguson
San Diego
CA, US
Louis S Biafore
San Diego
CA, US
Krishna M Gopinathan
San Diego
CA, US
Agent
Fenwick & West
Assignee
HNC Software
CA, US
IPC
G06F 15/30
View Original Source