Systems and methods are described herein for novel uses and/or improvements for designing user-specific interfaces using machine learning models. When a request to display certain data by an application is received, an application token and a user token may be retrieved and input into a machine learning model to obtain a prediction of a pre-defined user-application interface configuration. A user interface token for the application may then be generated. The user interface token may indicate user interface settings/configuration desired/preferred by a user. The user interface token may then be sent to the application to cause the application to display the data using user interface configurations within the user interface token.