Scoring candidates for set recommendation problems

Abstract

Implementations include systems and methods for scoring candidates for set recommendation problems. An example method includes repeating, for each code in code arrays for items in a set of items, determining a most common value for the code. In some implementations, the method includes determining that the most common value occurs with a frequency that meets an occurrence threshold and adding the code and the most common value to set-inclusion criteria. In other implementations, the method includes determining a value for the code from a code array for a seed item and adding the code and the most common value to set-inclusion criteria when the value for the code from the code array for the seed item matches the most common value. The method may also include evaluating a similarity with a candidate item based on the set-inclusion criteria and basing a recommendation regarding the candidate item on the similarity.

1 - 20 . (canceled) 
     
     
         21 . A method of providing recommendations of items, the method comprising:
 repeating, for each code in code arrays for items in a set of items:
 determining a most common value for the code, 
 determining whether the most common value occurs with a frequency that meets an occurrence threshold, and 
 adding the code and the most common value to set-inclusion criteria when the frequency meets the occurrence threshold; 
 evaluating a similarity with a candidate item based on the set-inclusion criteria; and 
 making a recommendation regarding the candidate item based on the similarity. 
   
     
     
         22 . The method of  claim 21 , wherein the items in the set are user profiles associated with an online community and the candidate item is a user profile not associated with the online community. 
     
     
         23 . The method of  claim 22 , wherein when the similarity meets a similarity threshold the online community is recommended to a user associated with the user profile not associated with the online community. 
     
     
         24 . The method of  claim 21 , wherein the recommendation regarding the candidate item includes an indication that the candidate item was automatically added to the set of items. 
     
     
         25 . The method of  claim 21 , wherein evaluating the similarity with the candidate item based on the set-inclusion criteria includes:
 determining the similarity by comparing a code array for the candidate item with the set-inclusion criteria; and   recommending the candidate item for inclusion in the set when the similarity meets a similarity threshold.   
     
     
         26 . The method of  claim 25 , wherein the similarity represents a ratio of set-inclusion criteria codes that match corresponding codes in the candidate item code array and a total quantity of codes in the set-inclusion criteria. 
     
     
         27 . The method of  claim 21 , wherein the frequency represents a percentage of items in the set sharing the value and the occurrence threshold is at least eighty-five percent. 
     
     
         28 . The method of  claim 21 , wherein the items in the set represent items a user accessed. 
     
     
         29 . The method of  claim 21 , wherein the codes in the code arrays represent hash codes derived from a vector similarity model. 
     
     
         30 . The method of  claim 21 , wherein the items in the set are user profiles associated with people responding to an advertisement and the candidate item is a user profile. 
     
     
         31 . A system comprising:
 at least one processor; and   memory storing instructions that, when executed by the at least one processor, cause the system to perform operations comprising:
 repeating, for each code in code arrays for items in a set of items: 
 determining a most common value for the code, 
 determining whether the most common value occurs with a frequency that meets an occurrence threshold, and 
 adding the code and the most common value to set-inclusion criteria when the frequency meets the occurrence threshold; 
 evaluating a similarity with a candidate item based on the set-inclusion criteria; and 
 making a recommendation regarding the candidate item based on the similarity. 
   
     
     
         32 . The system of  claim 31 , wherein the items in the set are user profiles associated with an online community and the candidate item is a user profile not associated with the online community, and wherein when the similarity meets a similarity threshold the online community is recommended to a user associated with the user profile not associated with the online community. 
     
     
         33 . The system of  claim 31 , wherein the recommendation regarding the candidate item includes an indication that the candidate item was automatically added to the set of items. 
     
     
         34 . The system of  claim 31 , wherein evaluating the similarity with the candidate item based on the set-inclusion criteria includes:
 determining the similarity by comparing a code array for the candidate item with the set-inclusion criteria; and   recommending the candidate item for inclusion in the set when the similarity meets a similarity threshold.   
     
     
         35 . The system of  claim 34 , wherein the similarity represents a ratio of set-inclusion criteria codes that match corresponding codes in the candidate item code array and a total quantity of codes in the set-inclusion criteria. 
     
     
         36 . The system of  claim 31 , wherein the items in the set represent items a user accessed. 
     
     
         37 . The system of  claim 31 , wherein the items in the set are user profiles associated with people responding to an advertisement and the candidate item is a user profile. 
     
     
         38 . A computer program product including instructions recorded on a non-transitory computer-readable storage medium and configured, when executed by at least one processor, to cause the at least one processor to:
 repeat, for each code in code arrays for items in a set of items:
 determine a most common value for the code, 
 determine whether the most common value occurs with a frequency that meets an occurrence threshold, and 
 add the code and the most common value to set-inclusion criteria when the frequency meets the occurrence threshold; 
 evaluate a similarity with a candidate item based on the set-inclusion criteria; and 
 make a recommendation regarding the candidate item based on the similarity. 
   
     
     
         39 . The computer program product of  claim 38 , wherein the items in the set are user profiles associated with an online community and the candidate item is a user profile not associated with the online community, and wherein when the similarity meets a similarity threshold the online community is recommended to a user associated with the user profile not associated with the online community. 
     
     
         40 . The computer program product of  claim 38 , wherein evaluating the similarity with the candidate item based on the set-inclusion criteria includes:
 determining the similarity by comparing a code array for the candidate item with the set-inclusion criteria; and   recommending the candidate item for inclusion in the set when the similarity meets a similarity threshold.