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.

Description

CROSS-REFERENCE TO RELATED PATENT APPLICATIONS[0001]This application is a continuation of U.S. application Ser. No. 14 / 195,062, filed Mar. 3, 2014; which is a continuation of U.S. application Ser. No. 12 / 393,383, filed Feb. 26, 2009, now U.S. Pat. No. 8,666,841; which is a Continuation of U.S. application Ser. No. 12 / 248,288, filed Oct. 9, 2008; which claims the benefit of U.S. Provisional Application No. 60 / 978,553, filed Oct. 9, 2007. The disclosures of all prior applications are incorporated herein by reference in their entirety.BACKGROUND OF THE INVENTION[0002]In numerous service industries today, fraud detection plays an important and prominent role. By way of example, and not limitation, industries that use fraud detection systems as an important component of their businesses include financial service industries, e-commerce retailers, and telecommunication industries.[0003]The role of fraud detection is critical today because of high monetary losses associated with fraud. For ...

AI Technical Summary

Benefits of technology

This approach enhances the sensitivity and accuracy of fraud detection, reducing false positives and the cost of identifying fraudulent events by using advanced indicators and automated learning engines to adapt to changing fraud patterns, thereby improving overall fraud detection efficiency.

Problems solved by technology

The role of fraud detection is critical today because of high monetary losses associated with fraud.

For example, for the 2006 calendar year, it is estimated that in the U.S. and Canada, over $3 billion dollars in revenue was lost in e-commerce payment transactions due to fraud.

Revenue losses from fraud are occurring despite companies using several fraud detection tools that aim to protect companies and customers from various forms of fraud.

This creates a backlash of customer dissatisfaction for each otherwise valid transaction that is rejected.

Also, despite automation advances in fraud detection systems, the majority of companies use some level of manual review, which further adds to the cost of combating fraud.

When a transaction is evaluated against a fraud model, and the model provides a statistical indication that the transaction may be fraudulent, the transaction can be marked as potentially fraudulent.

Despite current fraud detection systems, one limitation of such systems is their emphasis on traditional transaction details when detecting fraud.

Examples of verification errors may include: failed personal identification number (PIN) on an automatic teller machine (ATM), and failed PIN on a chip-and-pin point-of-sale (POS) terminal.

For instance, where a customer's account shows access to self-care via an internet device with a given IP address, later access by an alternate IP address, or use of the same IP address for accessing multiple user accounts, may suggest fraud.

Another challenge in the market for fraud detection systems is the dynamic nature of fraud.

Hence, in some instances, an initially effective fraud model can become ineffective without frequent updates to the underlying aspects of that model.

Images