SYSTEMS AND METHODS FOR SIMILAR ACCOUNT DETERMINATION
Systems, methods, and non-transitory computer-readable media can receive an indication that a user of a social networking system has interacted with a first account of the social networking system. A set of potential accounts is compiled based on account similarity criteria indicative of a similarity of each potential account to the first account. The set of potential accounts is ranked based on a machine learning model, and filtered based on filtering criteria. One or more similar account recommendations are presented to the user via a graphical user interface, the one or more similar account recommendations based on the ranking and the filtering.
1 . A computer-implemented method comprising:
receiving, by a computing system, an indication that a user of a social networking system has interacted with a first account of the social networking system;
compiling, by the computing system, a set of potential accounts based on account similarity criteria indicative of a similarity of each potential account to the first account;
ranking, by the computing system, the set of potential accounts based on a machine learning model;
filtering, by the computing system, the set of potential accounts based on filtering criteria; and
presenting, by the computing system, one or more similar account recommendations to the user via a graphical user interface, the one or more similar account recommendations based on the ranking and the filtering.
2 . The computer-implemented method of claim 1 , wherein the compiling a set of potential accounts comprises applying an account similarity criteria relating to determination of a co-follower score.
3 . The computer-implemented method of claim 1 , wherein the compiling a set of potential accounts comprises applying an account similarity criteria relating to determination of a historical follow-through rate.
4 . The computer-implemented method of claim 1 , wherein the compiling a set of potential accounts comprises applying an account similarity criteria relating to determination of a historical search co-visitation rate.
5 . The computer-implemented method of claim 1 , wherein each account similarity criterion of the account similarity criteria is associated with a subset of the set of potential accounts.
6 . The computer-implemented method of claim 1 , wherein the machine learning model produces a likelihood that the user will interact with a potential account based on user characteristics of the user.
7 . The computer-implemented method of claim 1 , wherein the filtering criteria comprise a criterion relating to a celebrity account designation.
8 . The computer-implemented method of claim 1 , wherein the filtering criteria comprise a criterion relating to filtering out accounts that the user has already interacted with.
9 . The computer-implemented method of claim 1 , wherein the filtering criteria comprise a criterion relating to filtering out accounts previously recommended to the user as a similar account.
10 . The computer-implemented method of claim 1 , further comprising training the machine learning model based on historical social networking interaction information.
11 . A system comprising:
at least one processor; and
a memory storing instructions that, when executed by the at least one processor, cause the system to perform a method comprising:
receiving an indication that a user of a social networking system has interacted with a first account of the social networking system;
compiling a set of potential accounts based on account similarity criteria indicative of a similarity of each potential account to the first account;
ranking the set of potential accounts based on a machine learning model;
filtering the set of potential accounts based on filtering criteria; and
presenting one or more similar account recommendations to the user via a graphical user interface, the one or more similar account recommendations based on the ranking and the filtering.
12 . The system of claim 11 , wherein the compiling a set of potential accounts comprises applying an account similarity criteria relating to determination of a co-follower score.
13 . The system of claim 11 , wherein the compiling a set of potential accounts comprises applying an account similarity criteria relating to determination of a historical follow-through rate.
14 . The system of claim 11 , wherein the compiling a set of potential accounts comprises applying an account similarity criteria relating to determination of a historical search co-visitation rate.
15 . The system of claim 11 , wherein each account similarity criterion of the account similarity criteria is associated with a subset of the set of potential accounts.
16 . A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:
receiving an indication that a user of a social networking system has interacted with a first account of the social networking system;
compiling a set of potential accounts based on account similarity criteria indicative of a similarity of each potential account to the first account;
ranking the set of potential accounts based on a machine learning model;
filtering the set of potential accounts based on filtering criteria; and
presenting one or more similar account recommendations to the user via a graphical user interface, the one or more similar account recommendations based on the ranking and the filtering.
17 . The non-transitory computer-readable storage medium of claim 16 , wherein the compiling a set of potential accounts comprises applying an account similarity criteria relating to determination of a co-follower score.
18 . The non-transitory computer-readable storage medium of claim 16 , wherein the compiling a set of potential accounts comprises applying an account similarity criteria relating to determination of a historical follow-through rate.
19 . The non-transitory computer-readable storage medium of claim 16 , wherein the compiling a set of potential accounts comprises applying an account similarity criteria relating to determination of a historical search co-visitation rate.
20 . The non-transitory computer-readable storage medium of claim 16 , wherein each account similarity criterion of the account similarity criteria is associated with a subset of the set of potential accounts.