US 11,734,755 B2
Dynamically determining real-time offers
Lauren Schwartz, Stamford, CT (US); Nomiki Petrolla, Stamford, CT (US); Alex Muller, Stamford, CT (US); Jorge Argueta, Stamford, CT (US); and Maya Mikhailov, Stamford, CT (US)
Assigned to SYNCHRONY BANK, Stamford, CT (US)
Filed by Synchrony Bank, Stamford, CT (US)
Filed on Dec. 31, 2020, as Appl. No. 17/139,435.
Claims priority of provisional application 62/955,737, filed on Dec. 31, 2019.
Prior Publication US 2021/0201404 A1, Jul. 1, 2021
Int. Cl. G06Q 40/00 (2023.01); G06Q 40/03 (2023.01); G06N 20/00 (2019.01)
CPC G06Q 40/03 (2023.01) [G06N 20/00 (2019.01)] 21 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving in real-time a set of user attributes associated with a user, wherein the set of user attributes correspond to user interactions with one or more applications and user account data;
dynamically training a machine learning model to generate a set of clusters from a dataset including historical data associated with a set of other users, wherein the historical data includes different sets of user attributes associated with the set of other users and previously provided real-time offers made to the set of other users;
dynamically identifying a cluster from the set of clusters based on the set of user attributes, wherein the cluster is identified by the machine learning model according to user attributes corresponding to users associated with the cluster and the set of user attributes associated with the user;
determining in real-time an offer for the user, wherein the offer is determined by the machine learning model and based on the identified cluster, and wherein the offer includes a dynamic range of parameters for customization of the offer;
providing the offer, wherein when the offer is received by a user device associated with the user, the user device presents the offer;
receiving an input corresponding to the offer, wherein the input includes selection of one or more parameters from the dynamic range of parameters;
sending an offer confirmation, wherein the offer confirmation corresponds to the selection of the one or more parameters; and
modifying the machine learning model in real-time, wherein the machine learning model is modified by updating the dataset to include the set of user attributes, the offer, and the selection of the one or more parameters, and wherein the updated dataset is used to update the set of clusters.