US 12,254,512 B2
Auto-adjudication process via machine learning
Holly Heglin, Toronto (CA); Haipeng Zhang, Toronto (CA); Matthew Forer, Burlington (CA); Judith Tamara Cirulis, Toronto (CA); Yuwei Liu, Vaughan (CA); Daerian Ashan Dilkumar, Toronto (CA); and Roy Duncan Pigott, Burlington (CA)
Assigned to The Toronto-Dominion Bank, Toronto (CA)
Filed by The Toronto-Dominion Bank, Toronto (CA)
Filed on Nov. 10, 2022, as Appl. No. 18/054,258.
Prior Publication US 2024/0161184 A1, May 16, 2024
Int. Cl. G06Q 40/00 (2023.01); G06Q 40/03 (2023.01)
CPC G06Q 40/03 (2023.01) 17 Claims
OG exemplary drawing
 
1. An apparatus comprising:
a network interface configured to receive a new application; and
a processor configured to:
assign different conditions to different nodes of a decision tree model through a software application within a development environment of a computing device, wherein edges between the different nodes comprise relationships between the different conditions;
iteratively execute the decision tree model on a plurality of applications within the development environment, wherein the decision tree model assigns different subsets of the plurality of applications to the different nodes in the decision tree model based on the different conditions assigned to the different nodes and content matching the different conditions included in the plurality of applications;
identify a first plurality of paths of nodes within the decision tree model which are assigned applications that have an approval rate above a threshold and a second plurality of paths of nodes within the decision tree model that have an approval rate below the threshold;
export the decision tree model from the development environment of the computing device and import the decision tree model into a runtime environment of the computing device;
extract a plurality of attributes from the new application and encode the plurality of attributes into a form that can be processed by the decision tree model;
query the decision tree model based on a call that includes the encoded plurality of attributes via an application programming interface (API);
map the new application to a subset of nodes within the first plurality of paths of nodes in the decision tree model based on the plurality of attributes and map the subset of nodes to one or more rules for auto-adjudicating the new application;
determine whether or not to approve the new application based on the subset of nodes; and
transmit notice of the determination associated with the new application.