FAT Forensics: A Python Toolbox for Implementing and Deploying Fairness, Accountability and Transparency Algorithms in Predictive Systems

TL;DR

FAT Forensics is an open source Python toolbox designed to evaluate and ensure fairness, accountability, and transparency in predictive machine learning systems, covering data, models, and predictions.

Contribution

The paper introduces FAT Forensics, a comprehensive Python toolkit that automatically assesses fairness, accountability, and transparency in predictive algorithms and pipelines.

Findings

Automates fairness, accountability, transparency evaluation

Supports inspection of data, models, and predictions

Open source and easy to integrate

Abstract

Predictive systems, in particular machine learning algorithms, can take important, and sometimes legally binding, decisions about our everyday life. In most cases, however, these systems and decisions are neither regulated nor certified. Given the potential harm that these algorithms can cause, their qualities such as fairness, accountability and transparency (FAT) are of paramount importance. To ensure high-quality, fair, transparent and reliable predictive systems, we developed an open source Python package called FAT Forensics. It can inspect important fairness, accountability and transparency aspects of predictive algorithms to automatically and objectively report them back to engineers and users of such systems. Our toolbox can evaluate all elements of a predictive pipeline: data (and their features), models and predictions. Published under the BSD 3-Clause open source licence, FAT Forensics is opened up for personal and commercial usage.