The widespread use of machine learning and data-driven algorithms for decision making has been steadily increasing over many years. The areas in which this is happening are diverse: healthcare, employment, finance, education, the legal system to name a few; and the associated negative side effects are being increasingly harmful for society. Negative data \emph{bias} is one of those, which tends to result in harmful consequences for specific groups of people. Any mitigation strategy or effective policy that addresses the negative consequences of bias must start with awareness that bias exists, together with a way to understand and quantify it. However, there is a lack of consensus on how to measure data bias and oftentimes the intended meaning is context dependent and not uniform within the research community. The main contributions of our work are: (1) a general algorithmic framework for defining and efficiently quantifying the bias level of a dataset with respect to a protected group; and (2) the definition of a new bias measure. Our results are experimentally validated using nine publicly available datasets and theoretically analyzed, which provide novel insights about the problem. Based on our approach, we also derive a bias mitigation algorithm that might be useful to policymakers.

翻译：随着机器学习与数据驱动算法在决策领域的广泛应用，其使用规模多年来持续增长。这些应用涉及医疗、就业、金融、教育、法律等多个领域，随之产生的负面社会影响也日益严重。数据偏见是其中突出问题之一，往往导致特定群体遭受不利后果。任何应对偏见负面影响的缓解策略或有效政策，都必须以认识偏见的存在为前提，并需要理解与量化偏见的方法。然而，目前学界对数据偏见的度量方式尚未达成共识，其含义常因具体情境而异，研究社区内部亦缺乏统一标准。本文的主要贡献包括：(1) 提出一个通用算法框架，用于定义并高效量化数据集相对于受保护群体的偏见程度；(2) 定义了一种新型的偏见度量标准。我们使用九个公开数据集进行实验验证，并结合理论分析，对相关问题提出了新的见解。基于所提方法，我们还推导出一种可供政策制定者使用的偏见缓解算法。