Invention Grant
- Patent Title: Visualizing machine learning model performance for non-technical users
-
Application No.: US16872640Application Date: 2020-05-12
-
Publication No.: US11556569B2Publication Date: 2023-01-17
- Inventor: Ellen R. Kolsto , Mark Marrara , Joel Russell Huffman , Stefan A. G. Van Der Stockt
- Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
- Applicant Address: US NY Armonk
- Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
- Current Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
- Current Assignee Address: US NY Armonk
- Agent Teddi E. Maranzano
- Main IPC: G06K9/62
- IPC: G06K9/62 ; G06F16/28 ; G06N3/08 ; G06N20/00 ; G06N5/04 ; G06F16/26

Abstract:
A method, system, and computer program product for visualizing a machine learning model are provided. A confusion matrix and model performance metric data are received from a classification model. For each data point in the confusion matrix, a corresponding pixel is generated. The pixels are grouped into clusters. Each cluster represents a label in the confusion matrix. A centroid is generated for each cluster. Using the model performance metric data, a misclassification indicator arrow is generated for each misclassified data point. The misclassification indicator arrow indicates both the predicted class and the actual class. The clusters, the centroids, and the misclassification indicator arrow are displayed as a graphical visualization of the machine learning model.
Public/Granted literature
- US20210357802A1 VISUALIZING MACHINE LEARNING MODEL PERFORMANCE FOR NON-TECHNICAL USERS Public/Granted day:2021-11-18
Information query