FAT Forensics: A Python Toolbox for Implementing and Deploying Fairness, Accountability and Transparency Algorithms in Predictive Systems
This addresses the problem of ensuring high-quality and reliable predictive systems for engineers and users, though it is incremental as it builds on existing FAT concepts with a new implementation.
The authors tackled the lack of regulation and certification in predictive systems by developing FAT Forensics, an open-source Python toolbox that inspects fairness, accountability, and transparency aspects across data, models, and predictions to automatically report them to engineers and users.
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.