CPC G06Q 40/03 (2023.01) [H04L 67/04 (2013.01)] | 20 Claims |
1. A computer-implemented method comprising:
selecting an activity machine learning model from a plurality of activity machine learning models based on a user activity duration corresponding to a user account, wherein:
the plurality of activity machine learning models are trained based on historical transaction activity to predict activity scores corresponding to user classes having different user activity durations, and
the plurality of activity machine learning models comprise neural networks or decision tree models;
generating an activity score utilizing the activity machine learning model from internal user activity data corresponding to the user account;
determining, utilizing a credit value model, a credit value range and one or more credit value conditions from the activity score; and
providing, for display via a computing device corresponding to the user account, credit values from the credit value range and the one or more credit value conditions.
|