FAT Forensics: A Python Toolbox for Algorithmic Fairness, Accountability and Transparency
arXiv:1909.05167 · doi:10.1016/j.simpa.2022.100406
Abstract
Today, artificial intelligence systems driven by machine learning algorithms can be in a position to take important, and sometimes legally binding, decisions about our everyday lives. In many cases, however, these systems and their actions are neither regulated nor certified. To help counter the potential harm that such algorithms can cause we developed an open source toolbox that can analyse selected fairness, accountability and transparency aspects of the machine learning process: data (and their features), models and predictions, allowing to automatically and objectively report them to relevant stakeholders. In this paper we describe the design, scope, usage and impact of this Python package, which is published under the 3-Clause BSD open source licence.
Homepage: https://fat-forensics.org/ Source Code: https://github.com/fat-forensics/fat-forensics/
References in corpus (10)
- Equality of Opportunity in Supervised Learning
- FACE: Feasible and Actionable Counterfactual Explanations
- AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
- Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approaches
- The Dataset Nutrition Label: A Framework To Drive Higher Data Quality Standards
- A Nutritional Label for Rankings
- A Reductions Approach to Fair Classification
- Defining Locality for Surrogates in Post-hoc Interpretablity
- FAT Forensics: A Python Toolbox for Implementing and Deploying Fairness, Accountability and Transparency Algorithms in Predictive Systems
- The impossibility of "fairness": a generalized impossibility result for decisions