Self-learning real-time prioritization of telecommunication fraud control actions

• US 6,597,775 B2
• Filed: 09/25/2001
• Issued: 07/22/2003
• Est. Priority Date: 09/29/2000
• Status: Active Grant

• Current Assignee: Fair Isaac Corporation
• Original Assignee: Fair Isaac Corporation
• Inventors: Holmes, Robert, Lawyer, Justin, Englund, Dirk, Zoldi, Scott, Pathria, Dimpy, Barclay, Alex, Roach, Tim
• Primary Examiner(s): Kuntz, Curtis
• Assistant Examiner(s): Tran, Quoc Duc
• Application Number:
  US09/963,358
• Publication Number:
  US 20020114435A1
• Time in Patent Office: 665 Days
• Field of Search: 379/1.01, 379/9.03, 379/114.01, 379/114.14, 379/32.01, 379/33, 379/112.01, 379/127.02, 379/188, 379/189, 379/196, 379/197, 379/115.01, 379/129, 379/133, 379/134, 379/137, 379/139, 455/410
• US Class Current: 379/114.14
• CPC Class Codes: H04M 15/00 Arrangements for metering, time-control or time indication ; Metering, charging or billing arrangements for voice wireline or wireless communications, e.g. VoIP
• CPC Class Codes: H04M 15/41 Billing record details, i.e. parameters, identifiers, structure of call data record [CDR]
• CPC Class Codes: H04M 15/47 Fraud detection or prevention means
• CPC Class Codes: H04M 15/58 based on statistics of usage or network monitoring
• CPC Class Codes: H04M 2215/0148 Fraud detection or prevention means
• CPC Class Codes: H04M 2215/0164 Billing record, e.g. Call Data Record [CDR], Toll Ticket[TT], Automatic Message Accounting [AMA], Call Line Identifier [CLI], details, i.e. parameters, identifiers, structure
• CPC Class Codes: H04M 2215/0188 Network monitoring; statistics on usage on called/calling number

Abstract

A predictive model system is used to detect telecommunications fraud. Call records (CDRs) provided by telephone companies are evaluated against specified rules. If one or more rules are matched, the system generates an alert. Pending alerts for a customer form a case, describing the caller'"'"'s calling patterns. A predictive model determines a score that is predictive of the likelihood that the call involved fraud. Cases are queued for examination by analysts.

Claims

1. A method for detecting telecommunications fraud comprising:

transmitting a full call data record (CDR) from a first telecommunications provider to a fraud detection system;

determining, by the fraud detection system, a likelihood that the full CDR is associated with fraudulent activity; and

transmitting a modified CDR and a fraud score from the fraud detection system to a second telecommunications provider, the modified CDR associated with the full CDR and the fraud score indicating the likelihood that the full CDR is associated with fraudulent activity.

2. The method of claim 1, further comprising transmitting the fraud score to the first telecommunications provider.

3. The method of claim 1, wherein the first telecommunications provider is a lessee of bandwidth from the second telecommunications provider.