Machine-learning architecture for defining end user audiences for automated online content selection

A system for determining users based on databases of webpage corpora for dynamic placement of content on available webpages hosted by third-party webservers, the system comprising:

• non-transitory media containing one or more databases including a corpus database configured to store a plurality of historic webpages and a campaign database configured to store campaign data;
• and
• a server having at least one processor coupled with memory, configured to:
• receive, from a client device, a context term with which to identify additional terms;
• generate a set of context terms including the context term by selecting from text of the corpus database one or more of a plurality of corpus terms having a relationship with the context term;
• calculate an implication score for a plurality of topic terms based on a co-occurrence between each topic term and one or more of the set of context terms on a set of historic webpages associated with the topic term;
• select a particular topic term from the plurality of topic terms based on the implication score for the particular topic term;
• determine an audience representing a set of one or more users having accessed at least one of the set of historic webpages associated with the particular topic term;
• and
• store the campaign data into the campaign database, the campaign data configured for executing a real-time bidding selection operation for an available webpage being accessed by a user of the audience hosted by one or more third-party servers during the real-time bidding selection operation.

A non-transitory computer readable medium containing machine-executable program instructions, wherein execution of the program instructions by one or more processors of a computer system causes the one or more processors to execute the steps of:

• receiving, from a client device, a context term with which to identify additional terms;
• generating a set of context terms including the context term by selecting from a corpus database one or more of a plurality of corpus terms having a relationship with the context term, the corpus database storing text extracted from a plurality of historic webpages;
• calculating an implication score for a plurality of topic terms based on a co-occurrence between each topic term and one or more of the set of context terms on a set of historic webpages associated with the topic term;
• selecting a particular topic term from the plurality of topic terms based on the implication score for the particular topic term;
• determining an audience representing a set of one or more users having accessed at least one of the set of historic webpages associated with the particular topic term;
• and
• storing, into a campaign database, campaign data comprising the audience representing the set of one or more users, the set of context terms, and the particular topic term, the campaign data configured for executing a real-time bidding selection operation for an available webpage being accessed by a user of the audience hosted by one or more third-party servers during the real-time bidding selection operation.