The What-If Tool: Interactive Probing of Machine Learning Models
IEEE Transactions on Visualization and Computer Graphics2019Vol. 26(1), pp. 1–1
Citations Over TimeTop 1% of 2019 papers
Abstract
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.
Related Papers
- → The Persuasive Power of Data Visualization(2014)216 cited
- → Visualization exploration and encapsulation via a spreadsheet-like interface(2001)96 cited
- → Application of Visualization and Graphic Analysis on 2-D River Numerical Simulation(2010)1 cited
- → Analysis and Example Implementation of Data Visualization Technology(2022)1 cited
- → A Visualization Primitive for Multiway Relationships(2016)