Generating and providing content stacks utilizing machine-learning models

A system comprising:

• at least one processor;
• and
• at least one non-transitory computer-readable storage medium comprising instructions that, when executed by the at least one processor, cause the system to:
• determine content-based signals indicating a composition of a plurality of content items accessible by a content management system;
• determine account-based signals indicating content interaction data and account data for a user account of the content management system;
• generate, based on the content-based signals and the account-based signals, a stack formulation graph comprising nodes representing the plurality of content items;
• and
• generate, from the stack formulation graph, a content stack comprising a set of content items corresponding to nodes satisfying a similarity threshold to a topic prompt.

A non-transitory computer-readable storage medium comprising instructions that, when executed by at least one processor, cause a computing device to:

• determine, from a plurality of content items associated with a user account of a content management system, content-based signals indicating a composition of the plurality of content items;
• determine, for the user account of the content management system, account-based signals indicating content interaction data and account data associated with the user account;
• generate, based on the content-based signals and the account-based signals, a stack formulation graph comprising:
• nodes representing the plurality of content items;
• and
• edges representing relationships of the plurality of content items;
• determine comparison metrics between at least a portion of the nodes of the stack formulation graph and a topic prompt;
• and
• generate a content stack comprising a set of content items corresponding to nodes having comparison metrics satisfying a similarity threshold.