Data-enabled success and progression system

A method comprising:

• storing, by the server within a database coupled to a network, by a server comprising a computing device coupled to the network and including a processor executing instructions within a memory, a plurality of user profiles, a risk model, a predefined risk threshold, and a plurality of action recommendations;
• selecting, by the server from the database, the risk model and at least one user attribute stored within a user profile in the plurality of user profiles;
• inputting, by the server, the at least one user attribute as a machine learning parameter into the risk model;
• receiving, by the server as output from the risk model, a risk score indicating a likelihood of a user failing to achieve an outcome;
• comparing, by the server, the risk score to the predefined risk threshold;
• responsive to a determination that the risk score is greater than the risk threshold:
• selecting, by the server from the database, at least one action recommendation in the plurality of action recommendations, the at least one action recommendation having at least one action recommendation attribute in common with the at least one user attribute;
• generating, by the server:
• a notification comprising the at least one action recommendation;
• and
• an updated graphical user interface (GUI), comprising the notification and at least one update to an order of presentation of at least one GUI component within an original GUI displayed on a user client device coupled to the network.

A system comprising:

• a server comprising a computing device coupled to a network and including a processor executing instructions within a memory which, when executed, cause the system to:
• store, within a database coupled to a network, a plurality of user profiles, a risk model, a predefined risk threshold, and a plurality of action recommendations;
• select, from the database, the risk model and at least one user attribute stored within a user profile in the plurality of user profiles;
• input the at least one user attribute as a machine learning parameter into the risk model;
• receive, as output from the risk model, a risk score indicating a likelihood of a user failing to achieve an outcome;
• compare the risk score to the predefined risk threshold;
• responsive to a determination that the risk score is greater than the risk threshold:
• select, from the database, at least one action recommendation in the plurality of action recommendations, the at least one action recommendation having at least one action recommendation attribute in common with the at least one user attribute;
• generate:
• a notification comprising the at least one action recommendation;
• and
• an updated graphical user interface (GUI), comprising the notification and at least one update to an order of presentation of at least one GUI component within an original GUI displayed on a user client device coupled to the network.