US 12,190,026 B2
Multi-platform model processing and execution management engine
Robert Andrew Nendorf, Chicago, IL (US); Nilesh Malpekar, Lincolnshire, IL (US); Mark V. Slusar, Chicago, IL (US); Joseph Alan Kleinhenz, Bolingbrook, IL (US); Robert Andrew Kreek, Seattle, WA (US); and Patrick O'Reilly, Belfast (GB)
Assigned to Allstate Insurance Company, Northbrook, IL (US)
Filed by Allstate Insurance Company, Northbrook, IL (US)
Filed on Sep. 28, 2020, as Appl. No. 17/034,807.
Application 17/034,807 is a continuation of application No. 15/673,872, filed on Aug. 10, 2017, granted, now 10,878,144.
Prior Publication US 2021/0012047 A1, Jan. 14, 2021
Int. Cl. G06F 30/20 (2020.01); G06F 9/46 (2006.01)
CPC G06F 30/20 (2020.01) [G06F 9/46 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computing device, comprising:
a processor; and
memory storing instructions that, when executed by the processor, cause the computing device to:
obtain input model data;
generate output data by processing the input model data using a machine learning model;
obtain expected output data corresponding to the input model data;
determine, based on the expected output data and the generated output data tracked over a predefined interval of time, that a degradation of the machine learning model is occurring at a first rate; and
when the first rate exceeds a forecasted degradation rate, transmit a notification indicating the machine learning model deviated from the expected output data.