Dynamically modifying digital content distribution campaigns based on triggering conditions and actions
The present disclosure is directed toward systems, methods, and non-transitory computer readable media that dynamically modify content distribution campaigns based on triggering conditions and actions. In particular, systems described herein can provide a user interface for display to a publisher device that includes a plurality of selectable options for setting triggering conditions and/or actions. For example, the disclosed systems can utilize a machine learning model to generate suggested triggering conditions and/or actions for one or more content distribution campaigns of a provider. Moreover, the disclosed systems can generate custom rules based on selected triggering conditions and actions and apply the custom rules during execution of digital content campaigns. For instance, the disclosed systems can monitor performance of content campaigns, detect triggering conditions, and dynamically modify digital content campaigns based on actions corresponding to the triggering conditions.
1. A method comprising:
utilizing a machine learning model to generate, from historical content distribution campaigns, predicted campaign rules comprising suggested conditions and suggested actions;
providing, for display within a user interface for defining custom rules, the suggested conditions in connection with a content distribution campaign;
providing, for display within the user interface, the suggested actions in connection with the content distribution campaign;
generating a custom rule associated with the content distribution campaign based on at least one condition selected from the suggested conditions and at least one action selected from the suggested actions;
executing the content distribution campaign by monitoring activity corresponding to the content distribution campaign to detect satisfaction of the at least one condition; and
in response to detecting satisfaction of the at least one condition, modifying the content distribution campaign according to the at least one action.
2. The method as recited in claim 1 , wherein monitoring activity corresponding to the content distribution campaign to detect satisfaction of the at least one condition comprises monitoring activity corresponding to the content distribution campaign to detect satisfaction of at least one of: a budget threshold, a cost threshold, or an impressions threshold.
3. The method as recited in claim 1 , wherein modifying the content distribution campaign according to the at least one action comprises modifying at least one of: a budget action, a target audience action, a bid amount action, or a pause content distribution campaign action.
4. The method as recited in claim 1 , further comprising, prior to providing the suggested conditions and providing the suggested actions, training the machine learning model to predict campaign rules by:
identifying the historical content distribution campaigns;
generating ground truth campaign rules based on the historical content distribution campaigns;
applying the machine learning model to the ground truth campaign rules to generate the predicted campaign rules; and
modifying parameters of the machine learning model based on a comparison of the ground truth campaign rules and the predicted campaign rules.
5. The method as recited in claim 4 , wherein:
each ground truth campaign rule comprises a ground truth condition and a ground truth action; and
each predicted campaign rule comprises a suggested condition and a suggested action.
6. The method as recited in claim 5 , further comprising, prior to providing the suggested conditions and providing the suggested actions:
identifying campaign data associated with the content distribution campaign; and
applying the trained machine learning model to the identified campaign data to generate the suggested conditions and the suggested actions.
7. The method as recited in claim 1 , further comprising:
providing, for display within the user interface, a notification option associated with the custom rule;
detecting a user selection of the notification option associated with the custom rule; and
in response to detecting satisfaction of the at least one condition associated with the custom rule, providing a notification according to the notification option.
8. The method as recited in claim 1 , further comprising, in response to modifying the content distribution campaign according to the at least one action, automatically executing the modified content distribution campaign.
9. The method as recited in claim 8 , further comprising:
updating campaign data associated with the modified content distribution campaign;
applying the machine learning model to the updated campaign data to generate at least one updated condition and at least one updated action; and
providing, for display within the user interface for defining custom rules, the at least one updated condition and the at least one updated action.
10. A system comprising:
at least one processor; and
at least one non-transitory computer readable storage medium storing instructions that, when executed by the at least one processor, cause the system to:
utilize a machine learning model to generate, from historical content distribution campaigns, predicted campaign rules comprising suggested conditions and suggested actions;
provide, for display within a user interface for defining custom rules, the suggested conditions in connection with a content distribution campaign;
provide, for display within the user interface, the suggested actions in connection with the content distribution campaign;
generate a custom rule associated with the content distribution campaign based on at least one condition selected from the suggested conditions and at least one action selected from the suggested actions;
execute the content distribution campaign by monitoring activity corresponding to the content distribution campaign to detect satisfaction of the at least one condition; and
in response to detecting satisfaction of the at least one condition, modify the content distribution campaign according to the at least one action.
11. The system as recited in claim 10 , wherein monitoring activity corresponding to the content distribution campaign to detect satisfaction of the at least one condition comprises monitoring activity corresponding to the content distribution campaign to detect satisfaction of at least one of: a budget threshold, a cost threshold, or an impressions threshold.
12. The system as recited in claim 10 , wherein modifying the content distribution campaign according to the at least one action comprises modifying at least one of: a budget action, a target audience action, a bid amount action, or a pause content distribution campaign action.
13. The system as recited in claim 10 , further storing instructions that, when executed by the at least one processor, cause the system to, prior to providing the suggested conditions and providing the suggested actions, train the machine learning model to predict campaign rules by:
identifying the historical content distribution campaigns;
generating ground truth campaign rules based on the historical content distribution campaigns;
applying the machine learning model to the ground truth campaign rules to generate the predicted campaign rules; and
modifying parameters of the machine learning model based on a comparison of the ground truth campaign rules and the predicted campaign rules.
14. The system as recited in claim 13 , wherein:
each ground truth campaign rule comprises a ground truth condition and a ground truth action; and
each predicted campaign rule comprises a suggested condition and a suggested action.
15. The system as recited in claim 14 , further storing instructions that, when executed by the at least one processor, cause the system to, prior to providing the suggested conditions and providing the suggested actions:
identify campaign data associated with the content distribution campaign; and
apply the trained machine learning model to the identified campaign data to generate the suggested conditions and the suggested actions.
16. A non-transitory computer readable medium storing instructions thereon that, when executed by at least one processor, cause a computer system to:
utilize a machine learning model to generate, from historical content distribution campaigns, predicted campaign rules comprising suggested conditions and suggested actions;
provide, for display within a user interface for defining custom rules, the suggested conditions in connection with a content distribution campaign;
provide, for display within the user interface, the suggested actions in connection with the content distribution campaign;
generate a custom rule associated with the content distribution campaign based on at least one condition selected from the suggested conditions and at least one action selected from the suggested actions;
execute the content distribution campaign by monitoring activity corresponding to the content distribution campaign to detect satisfaction of the at least one condition; and
in response to detecting satisfaction of the at least one condition, modify the content distribution campaign according to the at least one action.
17. The non-transitory computer readable medium of claim 16 , wherein monitoring activity corresponding to the content distribution campaign to detect satisfaction of the at least one condition comprises monitoring activity corresponding to the content distribution campaign to detect satisfaction of at least one of: a budget threshold, a cost threshold, or an impressions threshold.
18. The non-transitory computer readable medium of claim 16 , wherein modifying the content distribution campaign according to the at least one action comprises modifying at least one of: a budget action, a target audience action, a bid amount action, or a pause content distribution campaign action.
19. The non-transitory computer readable medium of claim 16 , further storing instructions thereon that, when executed by the at least one processor, cause the computer system to:
provide, for display within the user interface, a notification option associated with the custom rule;
detect a user selection of the notification option associated with the custom rule; and
in response to detecting satisfaction of the at least one condition associated with the custom rule, provide a notification according to the notification option.
20. The non-transitory computer readable medium of claim 16 , further storing instructions thereon that, when executed by the at least one processor, cause the computer system to, in response to modifying the content distribution campaign according to the at least one action, automatically execute the modified content distribution campaign.