US 12,287,766 B2
Systems and methods for machine learning-based data matching and reconciliation of information
Sadra Amiri Modghadam, Mission San Jose, CA (US); Chad Lavy, Delaware, OH (US); and Steve Turk, San Mateo, CA (US)
Assigned to JPMORGAN CHASE BANK, N.A., New York, NY (US)
Filed by JPMORGAN CHASE BANK, N.A., New York, NY (US)
Filed on Oct. 18, 2022, as Appl. No. 18/047,613.
Claims priority of provisional application 63/256,996, filed on Oct. 18, 2021.
Prior Publication US 2023/0120826 A1, Apr. 20, 2023
Int. Cl. G06F 16/00 (2019.01); G06F 16/215 (2019.01); G06F 16/22 (2019.01); G06F 16/25 (2019.01); G06F 16/27 (2019.01)
CPC G06F 16/215 (2019.01) [G06F 16/2255 (2019.01); G06F 16/25 (2019.01); G06F 16/27 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method for matching organizations to unique identifiers and managing the unique identifiers, comprising:
ingesting, by a company matching computer program, a plurality of records from a plurality of data sources;
identifying, by the company matching computer program, a company associated with each of the plurality of records;
assigning, by the company matching computer program, a unique identifiers to each uniquely identified company;
matching, by the company matching computer program, each of the plurality of records to one of the uniquely identified companies using a trained company matching machine learning engine, the trained company matching machine learning engine being trained on a matching record truth set;
identifying, by the company matching computer program, a primary company record in the matching records and associating other matching records with the primary company record;
matching, by a contact matching computer program, each of the plurality of records to a contact using a trained contact matching machine learning engine, the trained contact matching machine learning engine being trained on a matching contact truth set;
identifying, by the contact matching computer program, a primary contact record in the matching records and associating other matching records with the primary contact record;
generating, by an identity management computer program, a graph database using the unique identifiers as lattice work comprising information about a connection of the unique identifiers and the plurality of records;
receiving, by the company matching computer program, the contact matching computer program, and the identity management computer program, feedback on the matching companies, and matching contacts;
updating, by the identity management computer program, the graph database based on a quality assessment by a quality scoring computer program, the quality assessment comprising a number of matched independent sources;
updating, by the identity management computer program, the graph database based on the feedback on the matching companies and matching contacts;
updating, by the identity management computer program, the graph database based on a reliability of the plurality of data sources;
updating, by the company matching computer program, the trained company matching machine learning engine, and updating, by the contact matching computer program, the trained contact matching machine learning engine; and
generating, by a user interface executed on a computing device and in operative communication with the identity management computer program, a display of the graph database and a feedback interface.