US 12,093,266 B2
Machine learning model for recommending interaction parties
Dwipam Katariya, McLean, VA (US); Muhammad Uddin, San Bernardino, CA (US); Tania Cruz Morales, Washington, DC (US); Julian Duque, Arlington, VA (US); and Kimberly Stockley, Washington, DC (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Aug. 16, 2022, as Appl. No. 17/820,051.
Prior Publication US 2024/0061845 A1, Feb. 22, 2024
Int. Cl. G06F 16/00 (2019.01); G06F 16/2457 (2019.01); G06F 16/2458 (2019.01)
CPC G06F 16/24575 (2019.01) [G06F 16/2477 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system for recommending interaction parties, the system comprising:
one or more memories; and
one or more processors, communicatively coupled to the one or more memories, configured to:
receive user device interaction data associated with user device interactions between a user and a first subset of a plurality of interaction parties via a user device;
receive, from interaction party devices of a second subset of the plurality of interaction parties, interaction party device interaction data associated with interaction party device interactions between the user and the second subset of the plurality of interaction parties;
store, on a database, the user device interaction data and the interaction party device interaction data as historical interaction data associated with historical interactions of the user, wherein the historical interactions include the user device interactions and the interaction party device interactions;
provide the historical interaction data as input to a machine learning model, wherein the machine learning model is trained using supervised learning and the historical interactions of the user or historical interactions of one or more other users with one or more of the plurality of interaction parties;
receive an output, based on applying the machine learning model to the historical interaction data, that indicates one or more recommended interaction parties that are local entities to a geographic location associated with the user,
wherein the one or more recommended interaction parties are local entities to the geographic location based on having at least one location within a distance threshold of the geographic location and based on:
a quantity of locations of the one or more recommended interaction parties being less than a threshold, or
a revenue of the one or more recommended interaction parties, over a timeframe, being less than a threshold; and
transmit, to the user device, data indicating the one or more recommended interaction parties.