System and method for identity-based fraud detection using a plurality of historical identity records
View Patent ↗A method for identifying a fraudulent account application includes receiving a new account application comprising a plurality of identity-related fields and linking the identity-related fields associated with the new account application with identity-related fields associated with a plurality of historical account applications. The links form a graphical pattern on which statistical analysis can be performed to determine the likelihood that the new account application is fraudulent. The statistical analysis can comprise comparing the graphical pattern to a known, or normal graphical pattern in order to detect differences, or anomalies occurring in the graphical pattern associated with the new account application.
1. A method for generating a database of identity records for use in detecting fraud in relation to a new identity record comprising:
receiving a plurality of identity records, each comprising identity related information, from a plurality of client institutions;
storing the identity related information as fields within the plurality of identity records;
linking the fields associated with the plurality of identity records based on certain characteristics associated with each field,
generating a set of nodes based on fields associated with the plurality of identity records;
generating a set of edges composed of a pair of nodes sharing a common characteristic; and
forming a graphical network comprising the plurality of linked identity records, nodes, edges and link information.
2. The method of claim 1 , wherein the sets of said nodes and said edges based on plurality of linked identity records are stored as the graphical network.
3. The method of claim 2 , wherein the graphical network comprises a plurality of graphs defined by one or more sets of nodes and sets of edges.
4. The method of claim 3 , wherein the plurality of graphs are combined into a single graph.
5. The method of claim 3 , wherein the graphical network is stored as an adjacency matrix.
6. The method of claim 5 , wherein only the non-zero elements of the adjacency matrix are stored.
7. The method of claim 3 , further comprising storing auxiliary information with at least some of the nodes in the graphical network.
8. The method of claim 3 , further comprising storing auxiliary information with at least some of the edges comprising the graphical network.
9. The method of claim 3 , wherein the graphical network is stored as an adjacency matrix, storing only the non-zero elements of said matrix.
10. The method of claim 1 , wherein an edge is formed between nodes where the characteristic associated with the nodes are identical.
11. The method of claim 1 , wherein an edge is formed between nodes where the characteristic associated with the nodes are substantially similar.
12. The method of claim 1 , wherein the edges connecting the nodes are given fuzzy values.
13. The method of claim 12 , further comprising linking nodes based on a comparison of the fuzzy values associated with the edges.
14. The method of claim 1 , further comprising receiving new identity records, using the plurality of stored, linked identity records to evaluate the new identity record, and updating the plurality of stored, linked identity records with the new identity record.
15. A method for generating a database of identity records for use in detecting fraud in relation to a new identity record comprising:
receiving a plurality of identity records, each comprising identity related information, from a plurality of client institutions;
storing the identity related information as fields with in the plurality of identity records;
linking the fields associated with the plurality of identity records based on certain characteristics associated with each field,
generating a set of nodes based on fields associated with the plurality of identity records;
generating a set of edges composed of a pair of nodes sharing a common characteristic; and
storing the plurality of linked identity records and link information as a graphical network, the graphical network comprising a plurality of graphs defined by one or more sets of nodes and one or more sets of edges.
16. The method of claim 15 , wherein the plurality of graphs are combined into a single graph.
17. The method of claim 15 , wherein an edge is formed between nodes where the characteristic associated with the nodes are identical.
18. The method of claim 15 , wherein an edge is formed between where the characteristic associated with the nodes are substantially similar.
19. The method of claim 15 , wherein the edges connecting the nodes are given fuzzy values, and further comprising forming an edge between nodes based on a comparison of the fuzzy values associated with the edges.
20. The method of claim 15 , wherein the graphical network is stored as an adjacency matrix.
21. The method of claim 20 , wherein only the non-zero elements of the adjacency matrix are stored.
22. The method of claim 15 , further comprising storing auxiliary information with at least some of the nodes in the graphical network.
23. The method of claim 15 , further comprising storing auxiliary information with at least some of the edges comprising the graphical network.
24. The method of claim 15 , further comprising receiving a new identity records, using the plurality of stored, linked identity records to evaluate the new identity record, and updating the plurality of stored, linked identity records with the new identity record.
25. The method of claim 15 , wherein the graphical network is stored as an adjacency matrix, storing only the non-zero elements of said matrix.
26. A fraud detection center, comprising:
a portal configured to receive a new identity record;
an identity database comprising a plurality of identity records received from a plurality of client institutions, wherein the plurality of identity records form a graphical network of graph-structured data; and
an identity record processor coupled with the portal and the identity database, the identity record processor configured to evaluate the new identity record using the plurality of identity records, wherein the identity database comprises links between the plurality of identity records, the plurality of identity records each comprise a plurality of fields configured to store identity related information, each of the fields forms a node, the graphical network comprises a plurality of graphs defined by sets of nodes and sets of edges composed of pairs of nodes sharing a common characteristic.
27. The fraud detection center of claim 26 , wherein the plurality of graphs are combined into a single graph.
28. The fraud detection center of claim 26 , wherein an edge is formed between nodes when the nodes are identical.
29. The fraud detection center of claim 26 , wherein an edge is formed between nodes when a characteristic associated with the nodes is substantially similar.
30. The fraud detection center of claim 26 , wherein the characteristics associated with the edges connecting the nodes are given fuzzy values.
31. The fraud detection center of claim 30 , wherein edges are formed between nodes based on a comparison of the fuzzy values associated with the edges.
32. The fraud detection center of claim 26 , wherein the graphical network is stored as an adjacency matrix.
33. The fraud detection center of claim 32 , wherein only the non-zero elements of the adjacency matrix are stored.
34. The fraud detection center of claim 26 , wherein the identity database further comprises auxiliary information associated with at least some of the nodes in the graphical network.
35. The fraud detection center of claim 26 , wherein the identity database further comprises auxiliary information associated with at least some of the edges comprising the graphical network.
36. The fraud detection center of claim 26 , wherein the graphical network is stored as an adjacency matrix, storing only the non-zero elements of said matrix.