Social network risk analysis

• US 9,483,795 B1
• Filed: 07/25/2014
• Issued: 11/01/2016
• Est. Priority Date: 02/24/2011
• Status: Active Grant

• Current Assignee: Allstate Insurance Company (Allstate Corporation)
• Original Assignee: Allstate Insurance Company (Allstate Corporation)
• Inventors: Warden, Thomas, Peccei, Christian
• Primary Examiner(s): Poinvil, Frantzy
• Application Number:
  US14/341,173
• Time in Patent Office: 830 Days
• Field of Search: 705 3- 44
• US Class Current: 1/1
• CPC Class Codes: G06Q 10/0635 Risk analysis of enterprise or organisation activities
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

An enhanced social network module associated with an entity may create a social network for an individual, group, and/or organization. The module may then use the social network to determine risk associated with insuring a member of the social network. The determined risk may be used to calculate a rate for insuring the member. Additional features of the module may allow for the calculation of a group rate for insuring all members of the social network, the calculation of various centrality measures for each member of the social network, the calculation of a trust score for any given member, and the ability to poll members of the social network to determine various characteristics of any given member.

Claims

1. A method comprising:

using a processor associated with a computing device, generating a social network graph for an entity using data received from a server hosting a social network website, wherein the social network graph connects the entity to intermediate entities which are connected to a plurality of other entities;

using the processor, receiving data from at least one telematics device within at least one automobile associated with the entity, one of the intermediate entities, or one of the plurality of other entities,

using the processor, analyzing the social network graph and the data received from the at least one telematics device to determine risk associated with insuring the entity; and

using the processor and based upon the determined risk, determining a rate for insuring the entity.

2. The method of claim 1, wherein the connections are based on at least one characteristic related to the entity, the intermediate entities, and the plurality of other entities.

3. The method of claim 2, wherein the at least one characteristic comprises an age of at least one of the intermediate entities and the plurality of other entities.

4. The method of claim 2, wherein the at least one characteristic comprises a number of accidents involving at least one of the intermediate entities and the plurality of other entities during a predetermined time period.

5. The method of claim 2, wherein the at least one characteristic comprises a determination of whether at least one of the intermediate entities and the plurality of other entities smokes.

6. The method of claim 2, wherein the analyzing comprises estimating the at least one characteristic for the entity based on the at least one characteristic for the intermediate entities and the plurality of other entities.

7. The method of claim 6, wherein the estimating comprises estimating the at least one characteristic for the entity by weighting the at least one characteristic for the intermediate entities and the plurality of other entities based on distances of each of the intermediate entities and the plurality of other entities from the entity on the social network graph.

8. The method of claim 7, further comprising:

using the processor, excluding the at least one characteristic of one of the intermediate entities and the plurality of other entities from the estimation when the at least one characteristic for the one of the intermediate entities and the plurality of other entities is unknown.

9. The method of claim 2, wherein data related to the at least one characteristic is obtained from data received from the entity, the intermediate entities, or the plurality of other entities.

10. The method of claim 9, further comprising:

using the processor, providing discounts on services and goods in return for data related to the at least one characteristic.

11. The method of claim 1, wherein the rate comprises a group insurance rate that further applies to one or more of the intermediate entities and the plurality of other entities.

12. The method of claim 1, further comprising:

using the processor, providing a reward to one of the entity, the intermediate entities, and the plurality of other entities associated with a lowest risk rating.

13. The method of claim 1, further comprising:

using the processor, computing a betweeness centrality measure for the entity.

14. The method of claim 1, further comprising:

using the processor, computing a trust score for the entity based on a length of time that an insurance company has insured one or more of the intermediate entities and the plurality of other entities.

15. An apparatus comprising:

a processor; and

a memory storing computer-readable instructions that, when executed by the processor, cause the processor to perform a method comprising;

generating a social network graph for an individual using data received from a server hosting a social network website, wherein the social network graph connects the individual to intermediate individuals which are connected to a plurality of other individuals;

receiving data from at least one telematics device within at least one automobile associated with the individual, the plurality of other individuals, or a combination thereof;

estimating at least one characteristic of the individual by analyzing at least one characteristic of the intermediate individuals and the other individuals;

based on the estimated at least one characteristic of the individual and the data received from the at least one telematics device, determining risk associated with insuring the individual; and

based upon the determined risk, determining a rate for insuring the individual.

16. The apparatus of claim 15, wherein the memory further stores computer-readable instructions that, when executed by the processor, cause the processor to:

poll the intermediate individuals and the plurality of other individuals to estimate the at least one characteristic of the individual.

17. The apparatus of claim 16, wherein the memory further stores computer-readable instructions that, when executed by the processor, cause the processor to:

provide a reward to the intermediate individuals and the plurality of other individuals that participate in the polling.

18. The apparatus of claim 17, wherein the memory further stores computer-readable instructions that, when executed by the processor, cause the processor to:

compute a trust score for the individual based on lengths of time that the intermediate individuals and the plurality of other individuals have been policyholders at an insurance company.

19. A system comprising:

at least one telematics device within at least one automobile associated with an individual, a plurality of other individuals, or a combination thereof;

a processor; and

a memory storing computer-readable instructions that, when executed by the processor, cause the processor to perform a method comprising;

generating a social network graph for the individual using data received from a server hosting a social network website, wherein the social network graph connects the individual to intermediate individuals which are connected to the plurality of other individuals;

receiving data from the at least one telematics device;

determining at least one characteristic of the individual by analyzing at least one characteristic of one of the intermediate individuals or the plurality of other individuals;

based on the determined at least one characteristic of the individual and the data received from the at least one telematics device, determining risk associated with insuring the individual; and

based upon the determined risk, determining a rate for insuring the individual.

20. The system of claim 19, wherein the memory further stores computer-readable instructions that, when executed by the processor, cause the processor to:

poll at least one of the intermediate individuals and the plurality of other individuals to determine the at least one characteristic of the individual.