Fraud detection engine and method of using the same

Abstract

A fraud detection system and method uses unique indicators for detecting fraud that extend beyond traditional transaction-based indicators. These unique indicators may include environmental information about a customer or a transaction. Such indicators may be used to identify fraud events based on computer-executable instructions that evaluate fraud risk. Further, an improved fraud detection system may include a learning component with a feedback loop. Also, authenticating and other information may be directed to the system for updating indicating data, fraud models, and risk assessments.

What is claimed is: 
     
         1 . A computer-readable medium including computer-executable instructions to perform the following method steps:
 (a) storing indicators for identifying fraudulent events related to a customer account;   (b) defining one or more fraud models based on the indicators, wherein the one or more fraud models describe events indicative of fraudulent activity; and   (c) determining that an event is likely fraudulent, wherein the act of determining comprises:
 (i) comparing the event to the one or more fraud models; and 
 (ii) verifying that the event exceeds a threshold for similarity between the event and the one or more fraud models. 
   
     
     
         2 . The computer-readable medium of  claim 1 , wherein the computer-executable instructions further comprise the method steps of:
 (a) creating an assertion for the event determined to be likely fraudulent;   (b) communicating the assertion to an authorized user of the customer account;   (c) authenticating the authorized user of the customer account;   (d) receiving a response from the authorized user, wherein the response includes information revealing the nature of the event; and   (e) updating the one or more fraud models with the information provided in the response from the authorized user.   
     
     
         3 . The computer-readable medium of  claim 2 , wherein the act of communicating the assertion to an authorized user of the customer account comprises:
 (a) determining the authorized user's preferred mode of contact; and   (b) initiating a communication to the authorized user in accordance with the preferred mode of contact.   
     
     
         4 . The computer-readable medium of  claim 1 , wherein the indicators comprise a type of access channel used when accessing customer care operations. 
     
     
         5 . The computer-readable medium of  claim 4 , wherein the indicators further comprise biometric information. 
     
     
         6 . The computer-readable medium of  claim 5 , wherein the biometric information comprises navigation characteristics for the type of access channel used to access customer care operations. 
     
     
         7 . The computer-readable medium of  claim 1 , wherein the indicators comprise a graphical user interface comprising a field configured to capture a value indicating a level of suspicion associated with the event. 
     
     
         8 . The computer-readable medium of  claim 7 , wherein the suspicion is based at least in part on a direct interaction between an agent and a user attempting access to the customer account. 
     
     
         9 . The computer-readable medium of  claim 1 , wherein the indicators comprise a contact number used to reach a customer care agent. 
     
     
         10 . The computer-readable medium of  claim 1 , wherein the indicators comprise an email address used to reach a customer care agent. 
     
     
         11 . The computer-readable medium of  claim 1 , wherein the indicators comprise a number of transfers used to reach a customer care agent. 
     
     
         12 . A fraud detection system comprising:
 (a) a first computer-readable data storage including a first set of computer-executable instructions programmed to store indicators associated with a customer account, wherein the indicators comprise customer environmental information and are used to identify an event as likely fraudulent;   (b) a second computer-readable data storage including a first set of computer-executable instructions programmed to define one or more fraud models, wherein the one or more fraud models are based on the indicators and are indicative of fraud;   (c) a third computer-readable data storage including a set of computer-executable instructions programmed to establish a communication link with an authorized user of the customer account;   (d) a fourth computer-readable data storage including a set of computer-executable instructions programmed to authenticate the authorized user;   (e) a fifth computer-readable data storage including a set of computer-executable instructions programmed to receive information from the authorized user and update the one or more fraud models with the received information.   
     
     
         13 . The fraud detection system of  claim 12 , where the indicators for identifying fraud events comprise the type of access channel for customer care operations. 
     
     
         14 . The fraud detection system of  claim 12 , wherein the communication link is established according to the authorized user's contact preferences, wherein the authorized user's contact preferences are stored in a computer-readable data storage selected from the group consisting of: the first computer-readable data storage, the second computer-readable data storage, the third computer-readable data storage, and combinations thereof. 
     
     
         15 . The fraud detection system of  claim 12 , wherein the first computer-readable data storage includes a set of variables that serve as indicators for identifying the event as likely fraudulent, and further wherein at least one indicator is set by an agent based on the agent's suspicion that the event is fraudulent.