US 12,141,670 B2
Systems and methods for optimizing a machine learning model
Jason Lopatecki, Mill Valley, CA (US); and Aparna Dhinakaran, Dublin, CA (US)
Assigned to ARIZE AI, INC., Mill Valley, CA (US)
Filed by ARIZE AI, INC., Mill Valley, CA (US)
Filed on Jan. 26, 2023, as Appl. No. 18/159,905.
Application 18/159,905 is a continuation of application No. 17/658,737, filed on Apr. 11, 2022, granted, now 11,615,345.
Application 17/658,737 is a continuation of application No. 17/212,202, filed on Mar. 25, 2021, granted, now 11,315,043, issued on Apr. 26, 2022.
Prior Publication US 2023/0229971 A1, Jul. 20, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06K 9/62 (2022.01); G06F 18/2113 (2023.01); G06F 18/2115 (2023.01); G06N 20/00 (2019.01); G06T 7/00 (2017.01)
CPC G06N 20/00 (2019.01) [G06F 18/2113 (2023.01); G06F 18/2115 (2023.01)] 16 Claims
OG exemplary drawing
 
1. A system for optimizing a machine learning model, the system comprising:
a machine learning model that generates predictions based on at least one input feature vector, each input feature vector having one or more vector values; and
an optimization module with a processor and an associated memory, the optimization module being configured to:
create at least one slice of the predictions based on at least one vector value,
determine a precision metric of the slice based on a ratio of a number of true positives (TPs) and a sum of a number of TPs and false positives (FPs), and
optimize the machine learning model based on the precision metric.