Systems and methods for identifying illegitimate activities based on graph-based distance metrics

1. A computer-implemented method comprising:

generating, by a computing system, a bipartite node graph comprising a plurality of user account nodes, a plurality of edge nodes, and a plurality of connections connecting the plurality of user account nodes to the plurality of edge nodes, wherein each edge node of the plurality of edge nodes represents an edge connecting to at least two user account nodes of the plurality of user account nodes and each node of the at least two user account nodes is connected to at least one edge node of the plurality of edge nodes;

calculating, by the computing system, a distance score for each user account node of the plurality of user account nodes, wherein the distance score represents a minimum distance from a user account node of the plurality of user account nodes to a nearest illegitimate user account node of the plurality of user account nodes; and

determining, by the computing system, that a transaction is an illegitimate transaction based on the distance scores calculated for the each user account node of the plurality of user account nodes, wherein the calculating the distance score for each user account node of the plurality of user account nodes is performed iteratively, and further wherein after a threshold number of iterations, each user account node of the plurality of user account nodes that does not have a calculated distance score is assigned a distance score equal to a distance score cap value.

2. The computer-implemented method of claim 1 , wherein a subset of the plurality of user account nodes are illegitimate user account nodes.

3. The computer-implemented method of claim 1 , wherein the distance score is calculated based on a modified breadth-first search algorithm.

4. The computer-implemented method of claim 1 , wherein the plurality of edge nodes are associated with an edge characteristic.

5. The computer-implemented method of claim 4 , wherein the edge characteristic comprises at least one of: IP address, advertisement landing page ID, computing device identification information, or payment information.

6. The computer-implemented method of claim 5 , wherein each edge node of the plurality of edge nodes is associated with a particular IP address, a particular advertisement landing page ID, a particular set of computing device identification information, or a particular credit card Bank Identification Number (BIN).

7. The computer-implemented method of claim 1 , wherein the generating a bipartite node graph comprises generating a plurality of bipartite node graphs, each bipartite node graph of the plurality of bipartite node graphs comprising the plurality of user account nodes, the plurality of edge nodes, and the plurality of connections connecting the plurality of user account nodes to the plurality of edge nodes, each bipartite node graph of the plurality of bipartite node graphs is associated with a particular edge characteristic, and the calculating a distance score for each user account node of the plurality of user account nodes comprises calculating a plurality of distance scores for each user account node of the plurality of user account nodes, each distance score of the plurality of distance scores being calculated based on a respective one of the plurality of bipartite node graphs.

8. The computer-implemented method of claim 7 , wherein the distance score for each user account node comprises an average of the plurality of distance scores for the each user account node.

9. The computer-implemented method of claim 8 , wherein the determining that a transaction is an illegitimate transaction based on the distance scores comprises determining that a user account node associated with the transaction has a distance score below a distance score threshold.

10. A system comprising:

at least one processor; and

a memory storing instructions that, when executed by the at least one processor, cause the system to perform a method comprising:

generating a bipartite node graph comprising a plurality of user account nodes, a plurality of edge nodes, and a plurality of connections connecting the plurality of user account nodes to the plurality of edge nodes, wherein each edge node of the plurality of edge nodes represents an edge connecting to at least two user account nodes of the plurality of user account nodes and each node of the at least two user account nodes is connected to at least one edge node of the plurality of edge nodes;

calculating a distance score for each user account node of the plurality of user account nodes, wherein the distance score represents a minimum distance from a user account node of the plurality of user account nodes to a nearest illegitimate user account node of the plurality of user account nodes; and

determining that a transaction is an illegitimate transaction based on the distance scores calculated for the each user account node of the plurality of user account nodes, wherein the calculating the distance score for each user account node of the plurality of user account nodes is performed iteratively, and further wherein after a threshold number of iterations, each user account node of the plurality of user account nodes that does not have a calculated distance score is assigned a distance score equal to a distance score cap value.

11. The system of claim 10 , wherein a subset of the plurality of user account nodes are illegitimate user account nodes.

12. The system of claim 10 , wherein the distance score is calculated based on a modified breadth-first search algorithm.

13. The system of claim 10 , wherein the plurality of edge nodes are associated with an edge characteristic.

14. A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:

generating a bipartite node graph comprising a plurality of user account nodes, a plurality of edge nodes, and a plurality of connections connecting the plurality of user account nodes to the plurality of edge nodes, wherein each edge node of the plurality of edge nodes represents an edge connecting to at least two user account nodes of the plurality of user account nodes and each node of the at least two user account nodes is connected to at least one edge node of the plurality of edge nodes;

calculating a distance score for each user account node of the plurality of user account nodes, wherein the distance score represents a minimum distance from a user account node of the plurality of user account nodes to a nearest illegitimate user account node of the plurality of user account nodes; and

determining that a transaction is an illegitimate transaction based on the distance scores calculated for the each user account node of the plurality of user account nodes, wherein the calculating the distance score for each user account node of the plurality of user account nodes is performed iteratively, and further wherein after a threshold number of iterations, each user account node of the plurality of user account nodes that does not have a calculated distance score is assigned a distance score equal to a distance score cap value.

15. The non-transitory computer-readable storage medium of claim 14 , wherein a subset of the plurality of user account nodes are illegitimate user account nodes.

16. The non-transitory computer-readable storage medium of claim 14 , wherein the distance score is calculated based on a modified breadth-first search algorithm.

17. The non-transitory computer-readable storage medium of claim 14 , wherein the plurality of edge nodes are associated with an edge characteristic.