US 11,720,819 B2
Machine learning model error detection
Zhe Liu, San Jose, CA (US); Yufan Guo, San Jose, CA (US); Jalal Mahmud, San Jose, CA (US); and Rama Kalyani T. Akkiraju, Cupertino, CA (US)
Assigned to International Business Machines, Incorporated, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on May 29, 2020, as Appl. No. 16/888,356.
Prior Publication US 2021/0374601 A1, Dec. 2, 2021
Int. Cl. G06N 20/00 (2019.01); G06N 5/02 (2023.01)
CPC G06N 20/00 (2019.01) [G06N 5/02 (2013.01)] 25 Claims
OG exemplary drawing
 
1. A method for alerting a user to an erroneous prediction of a machine learning base model, the method comprising:
running the machine learning base model on a first input dataset to generate a pair of baseline predictions by the machine learning base model and to determine a local-level importance of a first explainable feature of the machine learning base model to a prediction class of the machine learning base model;
determining a global-level importance of the first explainable feature of the machine learning base model to the machine learning base model based on the local-level importance of the first explainable feature of the machine learning base model;
running the machine learning base model on a second input dataset to generate a new prediction by the machine learning base model;
determining an erroneousness designation for the new prediction based on the local-level importance of the first explainable feature of the machine learning base model and the global-level importance of the first explainable feature of the machine learning base model; and
communicating the new prediction and an indication of the erroneousness designation for the new prediction for presentation to the user.