Responsible AI Toolbox Capabilities
The Responsible AI Toolbox enables AI practitioners to design flexible and custom model assessment and decision-making workflows for their individual situation. It consists of different components with unique and complementary functionalities that can be plugged in together into a fluid and interactive experience.
The toolbox consists of four dashboards:
- Error Analysis dashboard, for identifying model errors and discovering cohorts of data for which the model underperforms. The dashboard is powered by Error Analysis.
- Explanation dashboard, for understanding model predictions. This dashboard is powered by InterpretML.
- Fairness dashboard, for understanding model’s fairness issues using various group-fairness metrics across sensitive features and cohorts. This dashboard is powered by Fairlearn.
- Responsible AI dashboard, a single pane of glass bringing together several mature RAI tools from the toolbox for a holistic responsible assessment and debugging of models and making informed business decisions. With this dashboard, you can identify model errors, diagnose why those errors are happening, and mitigate them. Moreover, the causal decision-making capabilities provide actionable insights to your stakeholders and customers.