Digital Media Environment for Analysis of Audience Segments

Abstract

Techniques and systems are described to enable users to optimize a digital marketing content system by analyzing an effect of components of digital marketing content on audience segments, environments of consumption, and channels of consumption. A computing device of an analytics system receives user interaction data describing an effect of user interaction with multiple items of digital marketing content on achieving an action for multiple audience segments. The analytics system identifies which of a plurality of components are included in respective items of digital marketing content. The analytics system generates data identifying different aspects that likely had an effect on the achieving an action on the items of digital marketing content, such as components of the items of digital marketing content, environments of consumption, channels of consumption. The analytics system outputs a result based on the data in a user interface.

What is claimed is: 
     
         1 . A method implemented by at least one computing device, the method comprising:
 receiving, by the at least one computing device, user interaction data for multiple segments of an audience, the user interaction data describing an effect of user interaction with a plurality of items of content on achieving an action;   identifying, by the at least one computing device, which of a plurality of components are included in respective ones of the plurality of items of content;   generating, by the at least one computing device, outcome data for the individual members of the audience describing whether the effect likely resulted from the multiple segments indicated in the segment data or from one or more of the plurality of components included in the respective ones of the plurality of items of content, the generating performed using a model trained using machine learning based on training data; and   outputting, by the at least one computing device, a result based on the outcome data for output in a user interface.   
     
     
         2 . The method as described in  claim 1 , wherein the identifying further comprises identifying one or more attributes of the one or more of the plurality of components, and wherein the outcome data further describes whether the effect likely resulted from the one or more attributes. 
     
     
         3 . The method as described in  claim 2 , wherein at least one of the one or more attributes is an intrinsic attribute that is inherent to the one or more of the plurality of components. 
     
     
         4 . The method as described in  claim 2 , wherein at least one of the one or more attributes is an attached attribute that associates a user or application to the one or more of the plurality of components. 
     
     
         5 . The method as described in  claim 1 , wherein the outcome data further identifies a particular audience segment of the multiple audience segments or a particular component of the plurality of components that likely resulted in the effect on achieving the action. 
     
     
         6 . The method as described in  claim 1 , wherein the outcome data further describes how the different components of the plurality of components affected different segments of the multiple segments at achieving the action. 
     
     
         7 . The method as described in  claim 1 , further comprising automatically generating an additional item of content based on the outcome data. 
     
     
         8 . The method as described in  claim 7 , wherein the additional item of content includes one or more components that included in the respective ones of the plurality of items of content that likely resulted in a desired effect on achieving the action. 
     
     
         9 . The method as described in  claim 1 , further comprising generating a content graph that connects users, content, and attributes for one of the plurality of items of content, the content graph identifying a plurality of components of the one of the plurality of items of content and including the outcome data and the result. 
     
     
         10 . A system comprising:
 a processing system; and   a computer-readable storage medium storing instructions that, responsive to execution by the processing system, causes the processing system to perform operations including:
 receiving user interaction data for multiple segments of an audience, the user interaction data describing an effect of user interaction with a plurality of items of content on achieving an action; 
 identifying which of a plurality of components are included in respective ones of the plurality of items of content; and 
 generating outcome data using a model trained using machine learning based on training data, the outcome data generated for the individual members of the audience describing whether the effect likely resulted from the multiple segments indicated in the segment data or from one or more of the plurality of components included in the respective ones of the plurality of items of content. 
   
     
     
         11 . The system as described in  claim 10 , wherein the identifying further comprises identifying one or more attributes of the one or more of the plurality of components, and wherein the outcome data further describes whether the effect likely resulted from the one or more attributes. 
     
     
         12 . The system as described in  claim 11 , wherein at least one of the one or more attributes is an intrinsic attribute that is inherent to the one or more of the plurality of components. 
     
     
         13 . The system as described in  claim 11 , wherein at least one of the one or more attributes is an attached attribute that associates a user or application to the one or more of the plurality of components. 
     
     
         14 . The system as described in  claim 10 , wherein the outcome data further identifies a particular audience segment of the multiple audience segments or a particular component of the plurality of components that likely resulted in the effect on achieving the action. 
     
     
         15 . The system as described in  claim 10 , wherein the outcome data further describes how the different components of the plurality of components affected different segments of the multiple segments at achieving the action. 
     
     
         16 . The system as described in  claim 10 , further comprising automatically generating an additional item of content based on the outcome data. 
     
     
         17 . The system as described in  claim 16 , wherein the additional item of content includes one or more components that included in the respective ones of the plurality of items of content that likely resulted in a desired effect on achieving the action. 
     
     
         18 . The system as described in  claim 10 , the operations further comprising generating a content graph that connects users, content, and attributes for one of the plurality of items of content, the content graph identifying a plurality of components of the one of the plurality of items of content and including the outcome data and the result. 
     
     
         18 . A system comprising:
 a model training model implemented at least partially in hardware of a computing device to train a model using machine learning, based on training data, to identify which aspects of a plurality of aspects contribute toward achieving an action by a segment of a plurality of segments of an audience, the training data identifying which of a plurality of components are included in respective ones of the plurality of items of content; and   a model use module implemented at least partially in hardware of the computing device to process user interaction data to generate a recommendation based on the trained model using machine learning, the recommendation indicating contributions of the plurality of components toward achieving the action for the segment of the plurality of segments of the audience.   
     
     
         19 . The system as described in  claim 18 , wherein the recommendation identifies one or more attributes of the plurality of components. 
     
     
         20 . The system as described in  claim 18 , wherein the model use module is configured to generate a content graph that connects users, components, and attributes for one of the plurality of items of content.