Generating graphical user interfaces comprising dynamic credit value user interface elements determined from a credit value model

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

• train an activity machine learning model by:
• inputting activity data that includes activity data variables of multiple user accounts into the activity machine learning model as training data, wherein the activity data comprises historical transaction activity or historical credit value utilization;
• receiving output of predicted activity scores from the activity machine learning model based on the input activity data;
• generating, utilizing a loss function, loss values for the activity machine learning model utilizing a comparison between the output of predicted activity scores and ground truth activity scores for the multiple user accounts from the training data;
• and
• adjusting weights of the activity data variables corresponding to the activity machine learning model based on the generated loss values to train the activity machine learning model to more effectively determine a risk of an account of the multiple user accounts, wherein the activity machine learning model comprises a neural network or a decision tree model;
• generate an activity score utilizing the trained activity machine learning model from internal user activity data corresponding to a user account;
• determine a dynamic credit value range utilizing a credit value model with the activity score generated from the trained activity machine learning model and a user activity condition corresponding to the user account by:
• determining, from an offer category matrix, an offer category for the user account utilizing a combination of the activity score and the user activity condition corresponding to the user account, wherein the offer category matrix maps activity scores and user activity conditions to one or more offer categories;
• and
• determining the dynamic credit value range by identifying one or more dynamic credit values that correspond to the determined offer category within a credit value matrix, wherein the credit value matrix comprises a mapping between offer categories and dynamic credit values;
• provide for display, within a graphical user interface of a computing device corresponding to the user account, a user interface slider comprising selectable credit values from the dynamic credit value range;
• and
• upon receiving a selection of a credit value from the computing device, provide for display, within the graphical user interface, one or more dynamic credit value conditions for the credit value determined utilizing the credit value model.

A system comprising:

• at least one processor;
• and
• at least one non-transitory computer-readable storage medium storing instructions that, when executed by the at least one processor, cause the system to:
• train an activity machine learning model by:
• inputting activity data that includes activity data variables of multiple user accounts into the activity machine learning model as training data, wherein the activity data comprises historical transaction activity or historical credit value utilization;
• receiving output of predicted activity scores from the activity machine learning model based on the input activity data;
• generating, utilizing a loss function, loss values for the activity machine learning model utilizing a comparison between the output of predicted activity scores and ground truth activity scores for the multiple user accounts from the training data;
• and
• adjusting weights of the activity data variables corresponding to the activity machine learning model based on the generated loss values to train the activity machine learning model to more effectively determine a risk of an account of the multiple user accounts, wherein the activity machine learning model comprises a neural network or a decision tree model;
• generate an activity score utilizing the trained activity machine learning model from internal user activity data corresponding to a user account;
• determine a dynamic credit value range utilizing a credit value model with the activity score generated from the trained activity machine learning model and a user activity condition corresponding to the user account by:
• determining, from an offer category matrix, an offer category for the user account utilizing a combination of the activity score and the user activity condition corresponding to the user account, wherein the offer category matrix maps activity scores and user activity conditions to one or more offer categories;
• and
• determining the dynamic credit value range by identifying one or more dynamic credit values that correspond to the determined offer category within a credit value matrix, wherein the credit value matrix comprises a mapping between offer categories and dynamic credit values;
• provide for display, within a graphical user interface of a computing device corresponding to the user account, a user interface slider comprising selectable credit values from the dynamic credit value range;
• and
• upon receiving a selection of a credit value from the computing device, provide for display, within the graphical user interface, one or more dynamic credit value conditions for the credit value determined utilizing the credit value model.