US 12,260,310 B2
Systems and methods for training and executing a machine learning model for analyzing an electronic database
Gena Womack, McLean, VA (US); and Tania Cruz Morales, McLean, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Dec. 13, 2021, as Appl. No. 17/643,904.
Prior Publication US 2023/0186171 A1, Jun. 15, 2023
Int. Cl. G06N 20/20 (2019.01); G06F 3/0483 (2013.01); G06F 3/04842 (2022.01); G06F 16/23 (2019.01)
CPC G06N 20/20 (2019.01) [G06F 3/0483 (2013.01); G06F 3/04842 (2013.01); G06F 16/2379 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for analyzing data using machine learning models, the method comprising:
receiving, by one or more processors, data associated with a request to add a new occasion to an electronic database, wherein:
the electronic database includes a plurality of occasions;
at least a portion of the plurality of occasions is associated with a timing value and a substance value;
the electronic database is associated with a first progress value determined based on the timing values and the substance values of the plurality of occasions;
the data associated with the request to add the new occasion is at least partially automatically generated by a first trained machine learning model; and
the first trained machine learning model is trained based on (i) training occasion data that includes information regarding one or more occasions associated with one or more electronic databases and (ii) progress value data including a progress value for each of the one or more electronic databases to learn relationships between the training occasion data and the progress value data, such that the first trained machine learning model is configured to use the learned relationships to generate a new occasion that will result in a second progress value that exceeds the first progress value;
receiving, by the one or more processors, data associated with the new occasion;
predicting, by a second trained machine learning model executed by the one or more processors, a timing value and a substance value for the new occasion,
wherein the second trained machine learning model is trained, based on (i) training occasion data that includes information regarding one or more occasions associated with one or more electronic databases and (ii) training value data that includes a prior timing value and substance value for each of the one or more occasions, to learn relationships between the training occasion data and the training value data, such that the second trained machine learning model is configured to use the learned relationships to determine the substance value and timing value for the new occasion in response to input of the data associated with a request to add a new occasion to the electronic database and data associated with the new occasion;
calculating, by the one or more processors, a second progress value for the electronic database based on the timing value and the substance value for the new occasion; and
upon determining that the second progress value exceeds the first progress value, causing, by the one or more processors, a graphical user interface to display a notification to add the new occasion to the electronic database.