Real-time detection of online new-account creation fraud using graph-based neural network modeling
US-12255916-B2 · Mar 18, 2025 · US
US12475259B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12475259-B2 |
| Application number | US-202217942969-A |
| Country | US |
| Kind code | B2 |
| Filing date | Sep 12, 2022 |
| Priority date | Sep 12, 2022 |
| Publication date | Nov 18, 2025 |
| Grant date | Nov 18, 2025 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
There are provided systems and methods for pairwise graph querying, merging, and computing for account linking. A service provider may provide an account graph system to identify pairwise similarities between different accounts based on shared data that may be identified through one or more linking characteristics. When providing pairwise graph similarities, a service provider may receive a query identifying two or more accounts and/or an account with a parameter for graph exploration and querying. The service provider may utilize connection, link, or relationship graphs, queried and generated using a graph database, to determine pairwise similarities between the designated seed account and one or more selected accounts. The graph may include vertices for different queried data points and edges connecting such queries, where directionality of the edges or other vectors may be used to identify links or hops between accounts for data querying and exploration.
Opening claim text (preview).
What is claimed is: 1 . A service provider system comprising: a non-transitory memory; and one or more hardware processors coupled to the non-transitory memory and configured to read instructions from the non-transitory memory to cause the service provider system to perform operations comprising: receiving a request identifying a first account and a request parameter for the request that is associated with account activities by the first account; querying, based on the request, a graph database for a first graph having a plurality of graph paths to additional accounts based on the request parameter; generating the first graph based on the querying, wherein the first graph comprises the plurality of graph paths that associate the first account to the additional accounts based on the account activities; identifying, from the first graph, a second account through a first one of the plurality of graph paths; determining that the second account is linked to the first account through the first one of the plurality of graph paths; merging the first graph with a second graph associated with the second account; and determining a risk analysis of the first account using a risk analysis model based at least on additional graph paths of the merged first and second graphs. 2 . The service provider system of claim 1 , wherein the querying the graph database comprises: executing, based on the request parameter, two graph queries to the graph database using a graph query language for account associations of the first account and the second account, and wherein the generating the first graph comprises merging the account associations into the first graph. 3 . The service provider system of claim 2 , wherein the first graph further comprises one of a plurality of graphs between the first account and the second account based on a plurality of query parameters. 4 . The service provider system of claim 2 , wherein the operations further comprise: determining a second one of the plurality of graph paths linking the first account and the second account, wherein the second one of the plurality of graph paths is less than or equal to a number of steps of the account activities. 5 . The service provider system of claim 1 , wherein the request parameter comprises one of an account identifier, an IP address, payment card information, or an account transactional history, and wherein the request parameter further comprises vertices for the first graph connected by edges to other vertices based on past interactions associated with the request parameter. 6 . The service provider system of claim 1 , wherein the first graph comprises a real-time graph and the identifying is based on a pairwise similarity of shared vertices connected by edges that are less than or equal to a threshold number of vertices. 7 . The service provider system of claim 1 , wherein the operations further comprise: generating a notification of the second account linked to the first account based on the determining that the second account is linked to the first account. 8 . The service provider system of claim 7 , wherein the operations further comprise: determining a number of the plurality of graph paths between the first account and the second account is less than or equal to a threshold path length, wherein the notification is further based on the number of the plurality of graph paths. 9 . The service provider system of claim 1 , wherein the request is associated with one of an account promotional strategy, a risk review operation, a fraud detection operation, or an account compliance check. 10 . A method comprising: receiving a request for a graph traversal of an account linkage graph from a first account to a plurality of other accounts, wherein the graph traversal comprises an account parameter for the account linkage graph that links the first account to the plurality of other accounts; determining, from a graph database, account asset links of the first account to other accounts based on the graph traversal; determining, from the graph traversal, a second account linked to the first account based on a threshold number of links between the first account and the second account; merging the account linkage graph with an additional graph associated with the second account; determining a risk analysis of the first account using a risk analysis model based at least on the merged account linkage graph; and outputting a notification of the second account linked to the first account based on the account parameter, the threshold number of links, and the risk analysis. 11 . The method of claim 10 , wherein the determining the account asset links comprises querying the graph database for a first graph associated with the account assets links of the first account. 12 . The method of claim 11 , further comprising: performing the graph traversal of the graph for the second account linked to the first account based on the threshold number of links. 13 . The method of claim 11 , wherein the determining the account access links further comprises querying the graph database for the additional graph associated with the second account. 14 . The method of claim 13 , wherein the merging the account linkage graph with the additional graph is based on overlapping graph paths between the account linkage graph and the additional graph. 15 . The method of claim 11 , wherein the graph traversal between the first account and the second account is less than or equal to the threshold number of links. 16 . A non-transitory machine-readable medium having stored thereon machine-readable instructions executable to cause a machine to perform operations comprising: receiving a query for an identification of a link between a first account and a second account, wherein the query comprises a first parameter associated with the first account and the second account; querying a graph database for a graph comprising the link between the first account and the second account, wherein the graph comprises a plurality of associations between the first account and the second account that include account data in common between the first account and the second account; merging the graph with an additional graph associated with the second account; determining, from the graph, a first association of the plurality of associations between the first account and the second account; determining that the first association includes a number of steps of the account data in common between the first account and the second account that is less than or equal to a threshold; determining a risk analysis of the first account using a risk analysis model based at least on the first association and the merged graph; and flagging the first account based on the risk analysis. 17 . The non-transitory machine-readable medium of claim 16 , wherein the querying the graph database comprises: requesting the graph from the graph database using a graph query language associated with the query and the first account; and determining the graph comprises vertices and edges between the vertices for the plurality of associations. 18 . The non-transitory machine-readable medium of claim 16 , wherein the operations further comprise: editing the graph based on one or more changes to the graph; and persisting the one or more changes to the graph with the graph database. 19 . The non-transitory machine-readable medium of claim 16 , wherein the first parameter is one of at least two parameters for
during internet communication, e.g. revealing personal data from cookies · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.