Bias, Fairness, and Accountability with AI and ML Algorithms
This addresses fairness and accountability issues in AI for researchers and practitioners, but is incremental as it reviews existing literature without new findings.
The paper tackles the problem of bias and unfairness in AI and ML algorithms by providing an overview of data bias types and sources, algorithmic unfairness, fairness metrics, and de-biasing techniques, but does not report specific results or numbers.
The advent of AI and ML algorithms has led to opportunities as well as challenges. In this paper, we provide an overview of bias and fairness issues that arise with the use of ML algorithms. We describe the types and sources of data bias, and discuss the nature of algorithmic unfairness. This is followed by a review of fairness metrics in the literature, discussion of their limitations, and a description of de-biasing (or mitigation) techniques in the model life cycle.