Estimating Performance for Binary Classification

We currently support the following standard metrics for bianry classification performance estimation:

  • roc_auc

  • f1

  • precision

  • recall

  • specificity

  • accuracy

For more information about estimating these metrics, refer to the Estimating Standard Performance Metrics for Binary Classification section.

We also support the following complex metrics for binary classification performance estimation:

  • confusion_matrix: a metric that has four components (TP, FP, FN, TN)

  • business_value: a metric that combines the four components of the confusion matrix using user-specified weights for each element, allowing for a connection between model performance and business results.

For more information about estimating these metrics, refer to the Estimating Confusion Matrix Elements for Binary Classification and Estimating Business Value for Binary Classification sections.