US 12,265,892 B2
Utilizing machine learning models to characterize a relationship between a user and an entity
Meghnath Sharma, Chantilly, VA (US); Vivek Bharatam, Aldie, VA (US); and Dinanath Nadkarni, Wake Forest, NC (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Dec. 31, 2020, as Appl. No. 17/139,507.
Prior Publication US 2022/0207420 A1, Jun. 30, 2022
Int. Cl. G06N 20/00 (2019.01); G06F 18/23213 (2023.01); G06F 18/2431 (2023.01)
CPC G06N 20/00 (2019.01) [G06F 18/23213 (2023.01); G06F 18/2431 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A system for machine learning-based classification, the system comprising:
one or more memories; and
one or more processors, coupled to the one or more memories, configured to:
identify an account associated with a user,
wherein the account is managed by an entity, and
wherein the account is identified based on a determination that one or more charges were assessed to the account by the entity;
determine, using an unsupervised machine learning model, a cluster of users to which the user belongs;
determine, using a supervised machine learning model, a classification of the user that indicates a level of quality of a relationship between the user and the entity,
wherein the supervised machine learning model is trained using a plurality of features derived from the cluster of users determined by using the unsupervised machine learning model;
determine, based on the classification determined using the supervised machine learning model, whether one or more adjustments are to be applied to the one or more charges,
wherein the determination of whether an adjustment is to be applied includes assessing historical engagement of the user and transaction patterns over a predetermined period, and
wherein assessing the historical engagement of the user and the transaction patterns includes assessing, over the predetermined period, one or more of: a balance of the account, occurrences of late actions, incomplete actions, timeliness of clearing account balances, a request to cancel an obligation, a request to reduce an obligation, or amounts of inflows and outflows in the account;
apply the one or more adjustments to the one or more charges based on determining that the one or more adjustments are to be applied to the one or more charges; and
cause funds in an amount of the one or more adjustments to be transferred to the account based at least in part on applying the one or more adjustments.