US Patent 11776013 Machine learning-based content predictor

Disclosed herein are a method and system that utilize a programmed content predictor to dynamically select electronic publishing content. In particular, the content predictor applies a selection model to select content for one or more selected webpages presented during an electronic transaction. The selection model utilizes a set of one or more machine learning models to select content based on calculated quality scores. The nature of the quality scores determined by the quality score model depend on the particular application. The predictor generates and populates a permutation quality table based on a set of selected content items and page variant, wherein the page variant defines locations of content positions within a webpage. The predictor then consumes the selection model to select a best permutation of content item-content position combinations to be returned for display on a webpage.