Invention Grant
- Patent Title: Machine learning model error detection
-
Application No.: US16888356Application Date: 2020-05-29
-
Publication No.: US11720819B2Publication Date: 2023-08-08
- Inventor: Zhe Liu , Yufan Guo , Jalal Mahmud , Rama Kalyani T. Akkiraju
- Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
- Applicant Address: US NY Armonk
- Assignee: International Business Machines, Incorporated
- Current Assignee: International Business Machines, Incorporated
- Current Assignee Address: US NY Armonk
- Agency: Conley Rose, P.C.
- Main IPC: G06N20/00
- IPC: G06N20/00 ; G06N5/02

Abstract:
A system includes a memory having instructions therein and at least one processor in communication with the memory. The at least one processor is configured to execute the instructions to determine a global-level importance magnitude value for a global-level importance of an explainable feature of a machine learning base model based on a first prediction of the machine learning base model. The at least one processor is also configured to execute the instructions to determine a global-level importance direction label for the global-level importance of the explainable feature based on the first prediction. The at least one processor is also configured to execute the instructions to generate a communication for presentation to a user based on a second prediction of the machine learning base model, based on the global-level importance magnitude value, and based on the global-level importance direction label.
Public/Granted literature
- US20210374601A1 MACHINE LEARNING MODEL ERROR DETECTION Public/Granted day:2021-12-02
Information query