US 12,307,512 B2
Systems and methods for executing models based on metadata
Yangming Chris Cai, Toronto (CA); and Sriram Rajaram, Toronto (CA)
Assigned to Bank of Montreal, Toronto (CA)
Filed by Bank of Montreal, Toronto (CA)
Filed on Aug. 18, 2022, as Appl. No. 17/890,903.
Claims priority of provisional application 63/237,901, filed on Aug. 27, 2021.
Prior Publication US 2023/0186384 A1, Jun. 15, 2023
Int. Cl. G06Q 40/03 (2023.01)
CPC G06Q 40/03 (2023.01) 18 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by one or more processors, a set of data containing relational database metadata, model data, and customer loan data;
configuring, by the one or more processors, a first model and a second model based on the model data and the metadata;
partitioning, by the one or more processors based on the relational database metadata, the customer loan data into first data and second data;
responsive to determining, by the one or more processors, an allocation of the first data to a first execution node of a plurality of execution nodes and the second data to a second execution node of the plurality of execution nodes, the allocation corresponding to a partition for each execution node in the plurality of execution nodes,
executing, by the one or more processors executing the first execution node of the allocation, the first model using the first data of the customer loan data to output a first credit risk score;
executing, by the one or more processors executing the second execution node of the allocation in parallel with the first execution node thereby improving performance of processing of the first data and the second data, the second model using the second data of the customer loan data to output a second credit risk score;
generating, by the one or more processors, a third credit risk score based on the first credit risk score and the second credit risk score; and
transmitting, by the one or more processors, a notification based on the third credit risk score.