Analyzing Churn Models with the Binary Classification Inspector

This workflow demonstrates the functionality of the Binary Classification Inspector node. It produces a complex view made of four different charts in order to compare, optimize and select predictions of different binary classifiers.

It is possible to compare a number of binary classifier machine learning models predicting the same target on the same test data using performance metrics and ROC curves. Here four machine learning models are used: Naive Bayes, Random Forest, Gradient Boosted Trees, Logistic Regression and Decision Tree.

By moving a threshold slider in the interactive view you can optimize a model by finding the best threshold given a performance metric of your choice.

It is possible to interactively select a given type of predictions (e.g. true positives) of one of the models and export them at the output of the node