US 12,136,050 B2
System and methods for prediction communication performance in networked systems
Vinay Dubey, Edison, NJ (US)
Assigned to THE BANK OF NEW YORK MELLON, New York, NY (US)
Filed by THE BANK OF NEW YORK MELLON, New York, NY (US)
Filed on Oct. 4, 2022, as Appl. No. 17/959,939.
Application 17/959,939 is a continuation of application No. 17/331,259, filed on May 26, 2021, granted, now 11,488,040.
Application 17/331,259 is a continuation in part of application No. 14/718,534, filed on May 21, 2015, abandoned.
Claims priority of provisional application 62/001,861, filed on May 22, 2014.
Prior Publication US 2023/0196218 A1, Jun. 22, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 10/063 (2023.01); G06F 11/34 (2006.01); G06F 18/25 (2023.01); G06N 3/04 (2023.01); G06N 5/025 (2023.01); G06N 5/04 (2023.01); G06N 7/01 (2023.01)
CPC G06Q 10/063 (2013.01) [G06F 11/3452 (2013.01); G06F 18/256 (2023.01); G06N 3/04 (2013.01); G06N 5/025 (2013.01); G06N 5/04 (2013.01); G06N 7/01 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A system for predicting communication settlement times across disparate computer networks, comprising:
storage circuitry configured to:
store a first tier of a machine learning architecture, wherein the first tier comprises:
a first machine learning model;
a second machine learning model; and
an aggregation layer for the first machine learning model and the second machine learning model;
store a second tier of the machine learning architecture, wherein the second tier comprises a plurality of rule sets for predicting communication settlement times;
control circuitry configured to:
receive a first data feed, wherein the first data feed corresponds to a first type of communication data;
receive a second data feed, wherein the second data feed corresponds to a second type of communication data;
generate a first feature input based on the first data feed;
generate a second feature input based on the second data feed;
input the first feature input into the first machine learning model to generate a first output;
input the second feature input into the second machine learning model to generate a second output;
generate, using the aggregation layer for the first machine learning model and the second machine learning model, a third feature input based on the first output and second output;
determine, based on the third feature input, a first rule set from a plurality of rule sets for predicting communication settlement times;
receive a first communication;
predict a first communication settlement time for the first communication based on the first rule set;
determine an aggregated communication load at a first time based on the first communication settlement time;
determine an amount of required performance availability based on the aggregated communication load; and
determine a recommendation based on the amount of required performance availability; and
cloud-based input/output configured to generate for display, on a user interface, the recommendation based on the first communication settlement time.