Abstract: The disclosure describes embodiments of systems, methods, and non-transitory computer readable storage media that utilize a variety of machine learning models and a base limit value model to generate user interface elements that transparently and efficiently present current and future base limit values for user accounts. For example, the disclosed systems can select from between multiple activity machine learning models and utilize the selected activity machine learning model with user activity data to determine an activity score. Then, the disclosed systems can determine a base limit value using a base limit value model that includes relations between activity scores and various user activity conditions. Additionally, the disclosed systems can generate user interface elements within a graphical user interface to display the determined base limit value, a subsequent base limit value, and user activity conditions to achieve the subsequent base limit value within a graphical user interface.