ConfusionVis: Comparative evaluation and selection of multi-class classifiers based on confusion matrices
In machine learning, the presumably best model is selected from a variety of model candidates generated by testing different model types, hyperparameters, or feature subsets. Relying on a single metric to select the best model does not consider class imbalances or the different costs of misclassifications.
Incorporating human knowledge to interactively analyse the per-class errors and class confusions over all model candidates
enables a more efficient training process and yields better models for given applications.
Paper (Open Access):
Andreas Theissler, Mark Thomas, Michael Burch, Felix Gerschner (2022),
ConfusionVis: Comparative evaluation and selection of multi-class classifiers based on confusion matrices,
Elsevier Knowledge-Based Systems, 2022, 108651, ISSN 0950-7051,
To import own data, create a CSV-file with a concatenation of confusion matrices.
Example for 3 classes and 3 models (columns = class labels, rows = predictions):
10,20,450 <— end of first confusion matrix