MACHINE-LANGUAGE-BASED MODEL FOR IDENTIFYING PEERS ON AN ONLINE SOCIAL NETWORK
Among other things, embodiments of the present disclosure discussed herein help to identify peers of various individuals and organizations who are members of an online social network. Groups of peers may be identified based on various criteria, and some embodiments may generate a probability score reflecting a confidence level that two or more members of the online social network are peers of one another.
1 . A system comprising:
a processor; and
memory coupled to the processor and storing instructions that, when executed by the processor, cause the system to perform operations comprising:
retrieving, from a database in communication with the system, information regarding a first member of an online social network;
retrieving, from the database, information regarding a second member of the online social network;
generating, based on the information regarding the first member and the information regarding the second member, a probability score reflecting a likelihood that the first member and the second member are part of a common group of peers; and
in response to the probability score exceeding a predetermined threshold, presenting at least a portion of the information regarding the first member and at least a portion of the information regarding the second member on a display screen of a computing device in communication with the system over the Internet.
2 . The system of claim 1 , wherein the computing device is a computing device associated with one of: the first member or the second member.
3 . The system of claim 1 , wherein the system generates a respective probability score reflecting a respective likelihood that the first member is part of common group of peers with each respective member in a plurality of members of the online social network, and wherein the generation of each respective probability score is based on the information regarding the first member and respective information for the respective member from the plurality of members.
4 . The system of claim 3 , wherein the system presents, on the display screen, at least a portion of the information regarding the first user and at least a portion of the information regarding each respective member for which the respective probability score exceeds the predetermined threshold.
5 . The system of claim 4 , wherein the system presents on the display screen, based on the respective probability scores, a ranked list of the respective members having a respective probability score that exceeds the predetermined threshold.
6 . The system of claim 1 , wherein generating the probability score includes generating a plurality of weighted scores based on a comparison of a respective plurality of characteristics from the information regarding the first member and the information regarding the second member.
7 . The system of claim 6 , wherein the first member of the online social network and the second member of the online social network are respective organizations, and wherein the plurality of characteristics includes one or more of: revenue for the respective organizations, sizes of the respective organizations, types of products sold by the respective organizations, types of employees employed by the respective organizations, locations of the respective organizations, and common connections within the online social network between the respective organizations.
8 . The system of claim 6 , wherein the first member of the online social network and the second member of the online social network are respective individuals, and wherein the plurality of characteristics includes one or more of: skills of the respective individuals, years of experience for the respective individuals, locations of the respective individuals, employment information for the respective individuals, titles of the respective individuals, education for the respective individuals, job functions for the respective individuals, and common connections within the online social network between the respective individuals.
9 . The system of claim 6 , wherein generating the plurality of weighted scores includes:
generating a first feature vector based on the respective plurality of characteristics from the information regarding the first member;
generating a second feature vector based on the respective plurality of characteristics the information regarding the second member; and
generating the plurality of weighted scores based on a comparison between the first feature vector and the second feature vector.
10 . A computer-implemented method comprising:
retrieving, by a computer system from a database in communication with the computer system, information regarding a first member of an online social network;
retrieving, from the database by the computer system, information regarding a second member of the online social network;
generating, by the computer system and based on the information regarding the first member and the information regarding the second member, a probability score reflecting a likelihood that the first member and the second member are part of a common group of peers; and
in response to the probability score exceeding a predetermined threshold, presenting, by the computer system, at least a portion of the information regarding the first member and at least a portion of the information regarding the second member on a display screen of a computing device in communication with the computer system over the Internet.
11 . The method of claim 10 , wherein the computing device is a computing device associated with one of: the first member or the second member.
12 . The method of claim 10 , wherein the system generates a respective probability score reflecting a respective likelihood that the first member is part of common group of peers with each respective member in a plurality of members of the online social network, and wherein the generation of each respective probability score is based on the information regarding the first member and respective information for the respective member from the plurality of members.
13 . The method of claim 12 , wherein the system presents, on the display screen, at least a portion of the information regarding the first user and at least a portion of the information regarding each respective member for which the respective probability score exceeds the predetermined threshold.
14 . The method of claim 13 , wherein the system presents on the display screen, based on the respective probability scores, a ranked list of the respective members having a respective probability score that exceeds the predetermined threshold.
15 . The method of claim 10 , wherein generating the probability score includes generating a plurality of weighted scores based on a comparison of a respective plurality of characteristics from the information regarding the first member and the information regarding the second member.
16 . The method of claim 15 , wherein the first member of the online social network and the second member of the online social network are respective organizations, and wherein the plurality of characteristics includes one or more of: revenue for the respective organizations, sizes of the respective organizations, types of products sold by the respective organizations, types of employees employed by the respective organizations, locations of the respective organizations, and common connections within the online social network between the respective organizations.
17 . The method of claim 15 , wherein the first member of the online social network and the second member of the online social network are respective individuals, and wherein the plurality of characteristics includes one or more of: skills of the respective individuals, years of experience for the respective individuals, locations of the respective individuals, employment information for the respective individuals, titles of the respective individuals, education for the respective individuals, job functions for the respective individuals, and common connections within the online social network between the respective individuals.
18 . The method of claim 15 , wherein generating the plurality of weighted scores includes:
generating a first feature vector based on the respective plurality of characteristics from the information regarding the first member;
generating a second feature vector based on the respective plurality of characteristics the information regarding the second member; and
generating the plurality of weighted scores based on a comparison between the first feature vector and the second feature vector.
19 . A tangible, non-transitory computer-readable medium storing instructions that, when executed by a server computer system, cause the server computer system to perform operations comprising:
retrieving, from a database in communication with the computer system, information regarding a first member of an online social network;
retrieving, from the database, information regarding a second member of the online social network;
generating, based on the information regarding the first member and the information regarding the second member, a probability score reflecting a likelihood that the first member and the second member are part of a common group of peers; and
in response to the probability score exceeding a predetermined threshold, presenting at least a portion of the information regarding the first member and at least a portion of the information regarding the second member on a display screen of a computing device in communication with the computer system over the Internet.
20 . The non-transitory computer-readable medium of claim 19 , wherein generating the probability score includes generating a plurality of weighted scores, and wherein generating the plurality of weighted scores includes:
generating a first feature vector based on the respective plurality of characteristics from the information regarding the first member;
generating a second feature vector based on the respective plurality of characteristics the information regarding the second member; and
generating the plurality of weighted scores based on a comparison between the first feature vector and the second feature vector.