Towards Auditing Unsupervised Learning Algorithms and Human Processes For Fairness
This addresses fairness auditing for algorithms and human processes, but appears incremental as it builds upon prior work in the area.
The paper tackles the problem of auditing unsupervised learning algorithms for fairness by extending existing work from binary to multi-group settings and more complex fairness definitions, though no concrete results or numbers are provided.
Existing work on fairness typically focuses on making known machine learning algorithms fairer. Fair variants of classification, clustering, outlier detection and other styles of algorithms exist. However, an understudied area is the topic of auditing an algorithm's output to determine fairness. Existing work has explored the two group classification problem for binary protected status variables using standard definitions of statistical parity. Here we build upon the area of auditing by exploring the multi-group setting under more complex definitions of fairness.