The most popular methods for measuring importance of the variables in a black box prediction algorithm make use of synthetic inputs that combine predictor variables from multiple subjects. These inputs can be unlikely, physically impossible, or even logically impossible. As a result, the predictions for such cases can be based on data very unlike any the black box was trained on. We think that users cannot trust an explanation of the decision of a prediction algorithm when the explanation uses such values. Instead we advocate a method called Cohort Shapley that is grounded in economic game theory and unlike most other game theoretic methods, it uses only actually observed data to quantify variable importance. Cohort Shapley works by narrowing the cohort of subjects judged to be similar to a target subject on one or more features. We illustrate it on an algorithmic fairness problem where it is essential to attribute importance to protected variables that the model was not trained on.
翻译:摘要:测量黑盒预测算法中变量重要性的最常见方法是利用合成输入数据,其中包括多个受试者的预测变量。这些输入数据可能是不可能的、不合理的,甚至逻辑上不可能的。因此,对这些情况的预测可能基于与黑盒算法的训练数据极为不同的数据。我们认为,当解释使用这些值时,用户不能信任对一个预测算法的决策进行解释。相反,我们倡导一种名为“同伴Shapley”的方法,该方法基于经济博弈理论,与大多数其他博弈理论方法不同,它仅使用实际观察到的数据来量化变量重要性。同伴Shapley的工作原理是缩小与目标受试者在一个或多个特征上被认为相似的受试者队列。我们将其应用于算法公平性问题,其中必须将重要性归因于未被模型训练的受保护变量。(翻译中英文专业术语未译出)