Optimizing and predicting campaign attributes

Abstract

Approaches provide for or automatically optimizing sponsored content campaigns for a sponsored content provider for a particular consumption category across different content publisher networks. For example, performance data for sponsored content campaigns can be used to train a model for a consumption category to determine allocation scores that quantify a relationship between target audiences and the consumption category. In response to a content placement request to initiate a sponsored content campaign associated with the consumption category, allocation scores can be determined and used to dynamically determine an allocation of resources to appropriate audiences or segments based at least in part upon the trained optimization model. A campaign template can be generated that includes the target audience(s), sponsored content, and respective budget allocation, and any other information for the campaign. The campaign can proceed based at least in part on the campaign template, and performance of the campaign can be monitored and analyzed during the campaign to optimize the campaign dynamically.