The Bias and Fairness Audit Toolkit for Machine Learning¶
Aequitas is an open-source bias audit toolkit for machine learning developers, analysts, and policymakers to audit machine learning models for discrimination and bias, and to make informed and equitable decisions around developing and deploying predictive risk-assessment tools.
Sample Jupyter Notebook¶
Explore bias analysis of the COMPAS data using the Aequitas library.
- Welcome to Aequitas
- Bias measures tailored to your problem
- Installation
- Understanding Input Data
- Understanding Output
- Understanding the Metrics
- Using the CLI
- Configurations
- Using Aequitas with Python
- Running the webapp locally
- Aequitas API
- Examples
- COMPAS Analysis using Aequitas
- Pre-Aequitas: Exploring the COMPAS Dataset
- Putting Aequitas to the task
- What biases exist in my model?
- How do I visualize bias in my model?
- What levels of disparity exist between population groups?
- How do I visualize disparities in my model?
- Visualizing disparities between groups in a single user-specified attribute for a single user-specified disparity metric
- Visualizing disparities between all groups for a single user-specified disparity metric
- Visualizing disparities between groups in a single user-specified attribute for default metrics
- Visualizing disparities between groups in a single user-specified attribute for all calculated disparity metrics
- Visualizing disparity between all groups for multiple user-specified disparity metrics
- How do I assess model fairness?
- How do I visualize bias metric parity?
- How do I visualize parity between groups in my model?
- Visualizing parity between groups in a single user-specified attribute for all calculated disparity metrics
- Researcher Check: Could the unfairness I am seeing be related to small group sizes in my sample?
- Visualizing parity between groups in a single user-specified attribute for all calculated disparity metrics
- Visualizing parity between all groups for multiple user-specified disparity metrics
- Visualizing parity between groups in multiple user-specified attributes
- The Aequitas Effect