Fraud Detection Systems

Application of Familiar Technology
To Minimize Losses



"Companies want to keep their losses quiet for
several reasons, the most compelling being that
customers quickly figure out who is footing the
bill for fraud." 

"Successful decision support systems have a
lot in common with successful fraud detection
systems.  The end user searches for behavior
associations and anomalies and makes corporate
decisions based on those results."

"Anomalies found by fraud detection systems
might include examples like the following:

o  The same person applying for a mortgage
    two or more times in one year for property
    on the same city block.

o  A credit card number used in cities 10,000
    miles apart within 24 hours.

o  A mobile phone number making a number of
    foreign calls for the first time in the six years
    since the service was begun.

"The first step to implementing a fraud detection
system is to 'codify' your known rules.  Then the
system must act quickly enough to identify and
prevent potential loss."

"The next step is to discover previously unknown
information in your organization's data -- Data
Mining."

"Fraud detection is the application of business
rules for the purpose of identifying potential fraud."