Freedom251 › AI Model Explainability Software
Aequitas
Plans
| Plan | Billed and limits | Price |
|---|---|---|
| Aequitas | Open-source toolkit · Python library | Free |
As dssg.github.io lists them, read 14 Nov 2026. The maker's own page has the final word.
Facts from Aequitas's own pages
- Audit capabilities
- It helps identify model biases, compare bias disparity between population groups, and visualize metrics and disparities. · dssg.github.io, 14 Nov 2026
- Database support
- The CLI can use database input configured with database credentials and an SQL query. · dssg.github.io, 14 Nov 2026
- Extensibility
- Users can add their own Fair ML methods through defined interfaces and method signatures. · github.com, 14 Nov 2026
- Fairness methods
- Aequitas Flow includes pre-, in-, and post-processing Fair ML methods for experimentation. · github.com, 14 Nov 2026
- Input requirements
- An audit uses a pandas DataFrame with a target label, model score, and categorical sensitive attributes; at least one sensitive attribute is required. · github.com, 14 Nov 2026
- Integration
- The experimentation workflow includes Optuna hyperparameter-optimization capabilities. · github.com, 14 Nov 2026
- Intended users
- The toolkit is aimed at machine-learning developers, analysts, and policymakers. · dssg.github.io, 14 Nov 2026
- License
- The GitHub repository identifies the project license as MIT. · github.com, 14 Nov 2026
- Local deployment
- The web application can be run locally after installing Aequitas. · dssg.github.io, 14 Nov 2026
- Metric flexibility
- Users can select confusion-matrix-based metrics relevant to their use case. · github.com, 14 Nov 2026
- Plots and reporting
- The toolkit provides plots for audit and experiment outcomes; its webapp and CLI can produce bias reports. · github.com, 14 Nov 2026
- Purpose
- Aequitas audits machine-learning models for discrimination and bias to inform decisions about predictive risk-assessment tools. · dssg.github.io, 14 Nov 2026
- Python compatibility
- The documentation states compatibility with Python 3.6 and later. · dssg.github.io, 14 Nov 2026
- Ways to use
- Aequitas is accessible through a Python API, command-line interface, and web application. · dssg.github.io, 14 Nov 2026
Where Aequitas stands on Freedom251
- AI Model Explainability Software#4 of 29