Calculating trust scores based on social graph statistics

• US 9,264,329 B2
• Filed: 03/03/2011
• Issued: 02/16/2016
• Est. Priority Date: 03/05/2010
• Status: Active Grant

• Current Assignee: www.TrustScience.com Inc.
• Original Assignee: Evan V. Chrapko, Leo M. Chan
• Inventors: Chrapko, Evan V, Chan, Leo M.
• Primary Examiner(s): Maung, Zarni
• Application Number:
  US13/582,387
• Publication Number:
  US 20130013807A1
• Time in Patent Office: 1,811 Days
• Field of Search: 709/232, 709/236, 709/240, 709/203, 709217-219, 709223-229, 709/250, 709238-239
• US Class Current: 1/1
• CPC Class Codes: H04L 41/12 Discovery or management of network topologies
• CPC Class Codes: H04L 43/0811 by checking connectivity
• CPC Class Codes: H04L 45/00 Routing or path finding of packets in data switching networks routing or path finding in wireless networks H04W40/00

Abstract

Systems and methods for calculating trust scores (trustworthiness) based on social graph statistics are described herein. The trust scores (trustworthiness) may be determined within or between individuals, groups, and/or entities represented by nodes in a social graph or other network. Social graph analytics may be used to determine connectivity statistics for each node in the social graph or network. The trust score may then be calculated by analyzing a number of paths connecting nodes in the network and the connectivity statistics associated with the nodes of the network. This trust score may then be used to make prospective real-world decisions, such as a request for credit or initiating a transaction.

Claims

1. A method for determining the network connectivity between a first node and a second node connected to the first node by at least one path, the method comprising:

identifying paths to the second node from the first node within a network community; and

using processing circuitry to;

determine a path score for each identified path;

determine a user connectivity value between the first node and the second node;

determine at least one connectivity statistics value for the first node;

combine the at least one connectivity statistics value and the user connectivity value between the first node and the second node to produce a network connectivity indication; and

output the network connectivity indication.

2. The method of claim 1 further comprising accessing a link threshold value, wherein identifying paths to the second node from the first node within a network community comprises identifying only those paths containing fewer links than the accessed link threshold value.

3. The method of claim 1 wherein the processing circuitry determines a path score for each identified path by:

dividing a combined path weight value by the square of the length of the identified path the number of links in the identified path; and

dividing the combination of one or more link weights of each link in an identified path by the sum of the path weights of all identified paths.

4. The method of claim 1 wherein the processing circuitry determines at least one connectivity statistics value for the first node by determining a mean path score and a path score standard deviation based on a node sample.

5. The method of claim 4 wherein the processing circuitry combines the at least one connectivity statistics value and the user connectivity value by determining the area under a normal curve based on the mean path score, the path score standard deviation, and the user connectivity value between the first node and the second node.

6. The method of claim 1 wherein the user connectivity value represents one of a user trust value or competency assessment.

7. The method of claim 6 further comprising using the processing circuitry to access third-party ratings data, wherein the network connectivity indication based, at least in part, on the third-party ratings information.

8. The method of claim 1 wherein identifying paths to the second node from the first node within a network community comprises accessing data from a social networking service.

9. The method of claim 1 wherein identifying paths to the second node from the first node within a network community comprises retrieving a pre-stored identification of the paths to the second node from the first node from a table in a database.

10. The method of claim 1 further comprising automatically making at least one network-based decision based, at least in part, on the network connectivity indication.

11. A system for determining the network connectivity between a first node and a second node connected to the first node by at least one path, the system comprising processing circuitry configured to:

identify paths to the second node from the first node within a network community;

determine a path score for each identified path;

determine a user connectivity value between the first node and the second node;

determine at least one connectivity statistics value for the first node;

combine the at least one connectivity statistics value and the user connectivity value between the first node and the second node to produce a network connectivity indication; and

output the network connectivity indication.

12. The system of claim 11 wherein the processing circuitry is further configured to access a link threshold value, wherein the processing circuitry identifies paths to the second node from the first node within a network community by identifying only those paths containing fewer links than the accessed link threshold value.

13. The system of claim 11 wherein the processing circuitry determines a path score for each identified path by:

dividing a combined path weight value by the square of the length of the identified path the number of links in the identified path; and

dividing the combination of one or more link weights of each link in an identified path by the sum of the path weights of all identified paths.

14. The system of claim 11 wherein the processing circuitry determines at least one connectivity statistics value for the first node by determining a mean path score and a path score standard deviation based on a node sample.

15. The system of claim 14 wherein the processing circuitry combines the at least one connectivity statistics value and the user connectivity value by determining the area under a normal curve based on the mean path score, the path score standard deviation, and the user connectivity value between the first node and the second node.

16. The system of claim 11 wherein the user connectivity value represents one of a user trust value or competency assessment.

17. The system of claim 16 wherein the processing circuitry is further configured to access third-party ratings data, wherein the network connectivity indication based, at least in part, on the third-party ratings data.

18. The system of claim 11 wherein the processing circuitry identifies paths to the second node from the first node within a network community by accessing data from a social networking service.

19. The system of claim 11 wherein the processing circuitry identifies paths to the second node from the first node within a network community by retrieving a pre-stored identification of the paths to the second node from the first node from a table in a database.

20. The system of claim 11 wherein the processing circuitry is further configured to automatically make at least one network-based decision based, at least in part, on the network connectivity indication.