Combining network analysis and predictive analytics

• US 9,660,869 B2
• Filed: 11/05/2014
• Issued: 05/23/2017
• Est. Priority Date: 11/05/2014
• Status: Active Grant

• Current Assignee: Fair Isaac Corporation
• Original Assignee: Fair Isaac Corporation
• Inventors: Calvert, Brian E., Ripley, John R., Betron, Michael
• Primary Examiner(s): Pollack, Melvin H
• Application Number:
  US14/533,968
• Publication Number:
  US 20160127195A1
• Time in Patent Office: 930 Days
• Field of Search: 709223, 709224
• CPC Class Codes: G06F 7/36 Combined merging and sorting
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 10/063 Operations research, analysis or management
• CPC Class Codes: G06Q 10/067 Enterprise or organisation modelling
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 41/145 involving simulating, designing, planning or modelling of a network
• CPC Class Codes: H04L 41/147 for predicting network behaviour
• CPC Class Codes: H04L 41/22 comprising specially adapted graphical user interfaces [GUI]
• CPC Class Codes: H04W 4/21 for social networking applications

Abstract

Records are obtained from sources and typed datasets are assembled based on the obtained records. Relationships are identified among the typed datasets and at least one network comprising nodes and edges are assembled based on the identified relationships. A network analyzer assembles a vector and the vector is passed to analytics. The analytics then generate an output that is provided to a user or other device in the form of data.

Claims

1. A method for implementation by one or more data processors forming part of at least one computing system, the method comprising:

obtaining, by at least one data processor, a plurality of records from a plurality of sources, the plurality of records comprising a plurality of types of data;

assembling, by at least one data processor, a plurality of typed datasets based on the obtained records, the assembling comprising;

extracting, from the plurality of records, typed data that corresponds to all data of a single type found in the obtained records;

assembling, by at least one data processor, at least one network comprising;

a plurality of nodes representing all instances of the typed data corresponding to a common event; and

a plurality of edges representing a relationship between the plurality of nodes, the relationship defining a connection between two or more of the plurality of nodes, where the edges comprise a weighting attribute representing a similarity between the nodes connected by the connection, the plurality of nodes and the plurality of edges stored as accessible memory objects in the at least one computing system;

assembling, by at least one data processor, a vector by using a network analyzer, the assembling comprising;

determining a required input format for an analytic configured to operate on the vector; and

generating, at the network analyzer, the vector comprising a subset of the typed data corresponding to the required input format;

passing, by at least one data processor, the vector to the analytic;

generating, by at least one data processor and the analytic, an output from the analytic based on at least the vector passed to the analytic, the output comprising electronic data corresponding to a result of the analytic operating on the vector; and

providing, by at least one data processor, data comprising the output.

2. The method of claim 1, wherein providing the data comprises at least one of:

displaying the data, transmitting the data to a remote node, storing the data, or loading the data into a memory.

3. The method of claim 1, wherein the analytic is a predictive analytic configured to generate electronic data corresponding to a predictive output based at least on a provided query and historical data for the typed data.

4. The method of claim 1, wherein the analytic is a decision analytic configured to provide electronic data corresponding to a decision generated by applying one or more rules to the vector comprising the subset of the typed data.

5. The method of claim 1, wherein the analytic is a descriptive analytic configured to perform operations comprising:

selecting a rule set to apply to the vector, to the network, or to both, by accessing a stored collection of rule sets;

generating a classification of the vector or the network based at least on the rule set; and

providing electronic data corresponding to the classification.

6. The method of claim 1, wherein the analytic includes a node analytic configured to perform operations comprising:

receiving a node reference identifying at least one of the plurality of nodes, and a query corresponding to the node;

generating a connectedness of the node based at least on a number of nodes that the node is connected to in the network; and

providing electronic data corresponding to the connectedness.

7. The method of claim 1, wherein the analytic includes an edge analytic configured to perform operations comprising:

receiving an edge reference and at least two node references; and

generating, from the edge reference and the at least two node references, a response to a query corresponding to a feature common to the at least two node references.

8. The method of claim 1, wherein the analytic includes a network analytic configured to perform operations comprising:

receiving a query for a number of the nodes in the network;

analyzing, at the network analytic, the network to determine the number of the nodes in the network; and

providing electronic data corresponding to the number of nodes in the network.

9. The method of claim 1, the assembling further comprising:

reducing, by at least one data processor, a dimensionality of the vector relative to the network to allow the analytic to receive the vector and generate the output.

10. The method of claim 1, the output comprising a reference to a stored copy of the network.

11. The method of claim 1 further comprising appending, to the vector, a time-series corresponding to at least one dimension of the vector to make the dimensionality of the vector compatible with the analytic.

12. A non-transitory computer program product storing instructions which, when executed by at least one data processor forming part of at least one computing system, result in operations comprising:

obtaining, by at least one data processor, a plurality of records from a plurality of sources, the plurality of records comprising a plurality of types of data;

assembling, by at least one data processor, a plurality of typed datasets based on the obtained records, the assembling comprising;

extracting, from the plurality of records, typed data that corresponds to all data of a single type found in the obtained records;

assembling, by at least one data processor, at least one network comprising;

a plurality of nodes representing all instances of the typed data corresponding to a common event; and

a plurality of edges representing a relationship between the plurality of nodes, the relationship defining a connection between two or more of the plurality of nodes, where the edges comprise a weighting attribute representing a similarity between the nodes connected by the connection, the plurality of nodes and the plurality of edges stored as accessible memory objects in the at least one computing system;

assembling, by at least one data processor, a vector by using a network analyzer the assembling comprising;

determining a required input format for an analytic configured to operate on the vector; and

generating, at the network analyzer, the vector comprising a subset of the typed data corresponding to the required input format;

passing, by at least one data processor, the vector to the one analytic;

generating, by at least one data processor and the analytic, an output from the analytic based on at least the vector passed to the analytic, the output comprising electronic data corresponding to a result of the analytic operating on the vector; and

providing, by at least one data processor, data comprising the output.

13. The computer program product of claim 12, wherein providing the data comprises at least one of:

displaying the data, transmitting the data to a remote node, storing the data, or loading the data into a memory.

14. The computer program product of claim 12 the assembling further comprising:

reducing, by at least one data processor, a dimensionality of the vector relative to the network to allow the analytic to receive the vector and generate the output.

15. The computer program product of claim 12 further comprising:

appending, to the vector, a time-series corresponding to at least one dimension of the vector to make the dimensionality of the vector compatible with the analytic.

16. A system comprising:

at least one programmable processor; and

a non-transient machine-readable medium storing instructions which, when executed by the at least one programmable processor, cause the at least one programmable processor to perform operations comprising;

obtaining, by at least one data processor, a plurality of records from a plurality of sources, the plurality of records comprising a plurality of types of data;

assembling, by at least one data processor, a plurality of typed datasets based on the obtained records, the assembling comprising;

extracting, from the plurality of records, typed data that corresponds to all data of a single type found in the obtained records;

assembling, by at least one data processor, at least one network comprising;

a plurality of nodes representing all instances of the typed data corresponding to a common event; and

a plurality of edges representing a relationship between the plurality of nodes, the relationship defining a connection between two or more of the plurality of nodes, where the edges comprise a weighting attribute representing a similarity between the nodes connected by the connection, the plurality of nodes and the plurality of edges stored as accessible memory objects in the at least one computing system;

assembling, by at least one data processor, a vector by using a network analyzer, the assembling comprising;

determining a required input format for an analytic configured to operate on the vector; and

generating, at the network analyzer, the vector comprising a subset of the typed data corresponding to the required input format;

passing, by at least one data processor, the vector to the one analytic;

generating, by at least one data processor and the analytic, an output from the analytic based on at least the vector passed to the analytic, the output comprising electronic data corresponding to a result of the analytic operating on the vector; and

providing, by at least one data processor, data comprising the output.

17. The system of claim 16, wherein the providing the data comprises at least one of:

displaying the data, transmitting the data to a remote node, storing the data, or loading the data into a memory.

18. The system of claim 16 the assembling further comprising:

reducing, by at least one data processor, a dimensionality of the vector relative to the network to allow the analytic to receive the vector and generate the output.

19. The system of claim 16 further comprising:

appending, to the vector, a time-series corresponding to at least one dimension of the vector to make the dimensionality of the vector compatible with the analytic.