Scoring methodology for purchasing card fraud detection
First Claim
1. A method for determining likelihood of a fraudulent purchasing card traction using a fraud database having fraud data used in known frauds, the method comprising:
- providing purchasing card applicant data for a purchasing card transaction, the purchasing card applicant data including a unique identifier portion having at least one unique identifier data element, a non unique identifier portion having at least one non-unique identifier data element, and a reference portion having at least one reference data element;
determining whether any of the purchasing card applicant data matches any of the fraud data used in known frauds of the fraud database;
determining which matched purchasing card applicant data occurs in the unique identifier portion, the non-unique identifier portion, and the reference portion;
determining which at least one unique identifier data element of the unique identifier portion matches any of the fraud data used in known frauds of the fraud database for each matched purchasing card applicant data occurring in the unique identifier portion;
determining which at least one non-unique identifier data element of the non-unique identifier portion matches any of the fraud data used in known frauds of the fraud database for each matched purchasing card applicant data occurring in the non-unique identifier portion;
determining which at least one reference data element of the reference portion matches any of the fraud data used in known frauds of the fraud database for each matched purchasing card applicant data occurring in the reference portion;
calculating a first match score based on each matched at least one unique identifier data element;
calculating a second match score based on each matched at least one non-unique identifier data element;
calculating a total match score by summing the first and second match scores; and
determining likelihood of the purchasing card transaction being fraudulent as a function of the total match score, wherein the purchasing card transaction is determined to be fraudulent when the total match score is greater than a predefined match score.
8 Assignments
0 Petitions
Accused Products
Abstract
A method and system is disclosed for scoring a match between applicant data provided by a client and data stored in a fraud database. The system includes a merchant application having a unique identifier portion, a non-unique identifier portion, and a reference portion, a processor having access to the merchant information for calculating a first match score based on a match occurring in the non-unique identifier portion, a second match score based on a match occurring in the unique identifier portion, and a third match score based on a match occurring in the reference portion, and wherein the processor sums the first, second, and third match scores to arrive at a total match score to determine whether the total match score has exceeded a predefined match score. If the predefined match score is exceed then an alert is sent to the client informing the client that a fraud match with a high degree of reliability has occurred.
160 Citations
18 Claims
-
1. A method for determining likelihood of a fraudulent purchasing card traction using a fraud database having fraud data used in known frauds, the method comprising:
-
providing purchasing card applicant data for a purchasing card transaction, the purchasing card applicant data including a unique identifier portion having at least one unique identifier data element, a non unique identifier portion having at least one non-unique identifier data element, and a reference portion having at least one reference data element;
determining whether any of the purchasing card applicant data matches any of the fraud data used in known frauds of the fraud database;
determining which matched purchasing card applicant data occurs in the unique identifier portion, the non-unique identifier portion, and the reference portion;
determining which at least one unique identifier data element of the unique identifier portion matches any of the fraud data used in known frauds of the fraud database for each matched purchasing card applicant data occurring in the unique identifier portion;
determining which at least one non-unique identifier data element of the non-unique identifier portion matches any of the fraud data used in known frauds of the fraud database for each matched purchasing card applicant data occurring in the non-unique identifier portion;
determining which at least one reference data element of the reference portion matches any of the fraud data used in known frauds of the fraud database for each matched purchasing card applicant data occurring in the reference portion;
calculating a first match score based on each matched at least one unique identifier data element;
calculating a second match score based on each matched at least one non-unique identifier data element;
calculating a total match score by summing the first and second match scores; and
determining likelihood of the purchasing card transaction being fraudulent as a function of the total match score, wherein the purchasing card transaction is determined to be fraudulent when the total match score is greater than a predefined match score. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A system for determining likelihood of a fraudulent purchasing card transaction using a fraud database having fraud data used in known frauds, the system comprising:
-
purchasing card applicant data for a purchasing card transaction, the purchasing card applicant data including a unique identifier portion having at least one unique identifier data element, a non-unique identifier portion having at least one non-unique identifier data element, and a reference portion having at least one reference data element;
a processor operable for determining whether any of the purchasing card applicant data matches any of the fraud data used in known frauds of the fraud database and for determining which matched purchasing card applicant data occurs in the unique identifier portion, the nonunique identifier portion, and the reference portion;
wherein the processor is further operable for determining which at least one unique identifier data element of the unique identifier portion matches any of he fraud data used in known frauds of the fraud database for each matched purchasing card applicant data occurring in the unique identifier portion, determining which at least one non-unique identifier data element of the non-unique identifier portion matches any of the fraud data used in known frauds of the fraud database for each matched purchasing card applicant data occurring in the non-unique identifier portion, and determining which at least one reference data element of the reference portion matches any of the fraud data used in known frauds of the fraud database for each matched purchasing card applicant data occurring in the reference portion;
wherein the processor is further operable for calculating a first match score based on each matched at least one unique identifier data element, calculating a second match score based on each matched at least one non-unique identifier data element, and calculating a total match score by summing the first and second match scores;
wherein the processor is further operable for determining likelihood of the purchasing card transaction being fraudulent as a function of the total match score, wherein the purchasing card transaction is determined to be fraudulent when the total match score is greater than a predefined match score. - View Dependent Claims (11, 12, 13, 14, 15, 16, 17, 18)
-
Specification