Machine learning for targeting help content

One or more non-transitory computer-readable media storing computer-executable instructions that, when executed by at least one processor, perform a method of recommending help content within a group-based communication system, the method comprising:

• receiving user interaction data comprising prior interactions of a user with one or more features of a plurality of features of the group-based communication system;
• generating, using a trained machine learning model, a list of recommended help content based on the user interaction data
• wherein the trained machine learning model is trained based on:
• a first set of data that includes prior interaction data for a plurality of prior users and the plurality of features of the group-based communication system, and
• a second set of data that includes historical user engagement data including engagement with the help content associated with the plurality of features, to learn relationships between the first set of data and the second set of data, such that the trained machine learning model is configured to use the relationships to generate the list of recommended help content for the user upon input of the user interaction data of the user;
• determining a time at which the user is predicted to perform an action relating to a feature of the plurality of features that is associated with the list of recommended help content;
• and
• displaying, at or prior to the time and via a graphical user interface, the list of recommended help content.

A system comprising:

• at least one processor;
• and
• one or more non-transitory computer-readable media storing computer-executable instructions that, when executed by the at least one processor, perform a method of recommending help content within a group-based communication system, the method comprising:
• receiving user interaction data comprising prior interactions of a user with one or more features of a plurality of features of the group-based communication system;
• generating, using a trained machine learning model, a list of recommended help content based on the user interaction data,
• wherein the trained machine learning model is trained based on:
• a first set of data that includes prior interaction data for a plurality of prior users and the plurality of features of the group-based communication system, and
• a second set of data that includes historical user engagement data including engagement with the help content associated with the plurality of features, to learn relationships between the first set of data and the second set of data, such that the trained machine learning model is configured to use the relationships to generate the list of recommended help content for the user upon input of the user interaction data of the user;
• displaying, via a graphical user interface, the list of recommended help content;
• and
• determining, based at least in part on the user interaction data, an action associated with a feature of the plurality of features that the user has initiated but that has yet to perform, wherein the list of recommended help content includes second help content related to the action.