Algorithmic decisions often result in scoring and ranking individuals, to determine credit worthiness, desirability for college admissions and employment, and attractiveness as dating partners. As is often the case with algorithmic processes, rankers can, and do misbehave | they discriminate against individuals and members of protected groups, and violate privacy. Additionally, ranked results are often unstable | small changes in the input data or in the ranking methodology may lead to drastic changes in the ranked output, making the result uninformative. Rankers tend to be opaque, making discrimination, lack of stability, and privacy violations difficult to detect. Despite the ubiquity of rankers, there is, to the best of our knowledge, no technical work that focuses on making rankers transparent. The goal of our project is to ll this gap.
In this project we will build Ranking Facts, a Web-based application that generates a nutritional label for rankings. Our nutritional label will explain ranked outputs to a user, demystifying the ranking process and its results. This work will give transparency tools to every-day Web users, designers of ranking schemes and regulators, while also making critical contributions to computer science. All outcomes of this work will be made publicly available in the open source.