The What-if Tool: Code-Free Probing of Machine Learning Models

How would changes to a datapoint affect my model’s prediction? Does it perform differently for various groups–for example, historically marginalized people? How diverse is the dataset I am testing my model on?

The What-If Tool, showing a set of 250 face pictures and their results from a model that detects smiles. Exploring what-if scenarios on a datapoint. Comparing counterfactuals.

Comparing the performance of two slices of data on a smile detection model, with their classification thresholds set to satisfy the “equal opportunity” constraint. Detecting misclassifications: A multiclass classification model, which predicts plant type from four measurements of a flower from the plant. The tool is helpful in showing the decision boundary of the model and what causes misclassifications.

This model is trained with the UCI iris dataset.

Source: googleblog.com