Dynamically modifying digital content distribution campaigns based on triggering conditions and actions

A method comprising:

• utilizing a machine learning model to generate predicted campaign rules for a content distribution campaign, the predicted campaign rules comprising a plurality of predicted conditions and a plurality of predicted actions for the plurality of predicted conditions;
• monitoring activity of the content distribution campaign to automatically detect whether a first condition from the plurality of predicted conditions has been triggered, the first condition corresponding to a first action from the plurality of predicted actions;
• and
• in response to detecting that the first condition has been triggered, automatically modifying the content distribution campaign according to the first action.

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:

• identify one or more features of a digital distribution campaign;
• utilize a machine learning model with the one or more features of the digital distribution campaign to determine one or more predicted campaign rules comprising one or more predicted campaign conditions and corresponding predicted action recommendations that increase a likelihood of a user population engaging with a content distribution campaign based on one or more monitored user activities;
• and
• based on the determined one or more predicted campaign rules, modify the content distribution campaign by applying an action from the predicted action recommendations when a campaign condition from the one or more predicted campaign conditions is triggered by the one or more monitored user activities, wherein the action comprises increasing or decreasing a bid amount for the content distribution campaign.