The What-If Tool: Interactive Probing of Machine Learning Models
This tool addresses the problem of model interpretability and fairness for ML practitioners, though it is incremental as it builds on existing visualization and analysis techniques.
The paper tackles the challenge of understanding machine learning model performance across diverse inputs by introducing the What-If Tool, an open-source application that enables practitioners to probe, visualize, and analyze ML systems with minimal coding, and reports on its real-life usage in various organizations.
A key challenge in developing and deploying Machine Learning (ML) systems is understanding their performance across a wide range of inputs. To address this challenge, we created the What-If Tool, an open-source application that allows practitioners to probe, visualize, and analyze ML systems, with minimal coding. The What-If Tool lets practitioners test performance in hypothetical situations, analyze the importance of different data features, and visualize model behavior across multiple models and subsets of input data. It also lets practitioners measure systems according to multiple ML fairness metrics. We describe the design of the tool, and report on real-life usage at different organizations.