Feature attributions are a common paradigm for model explanations due to their simplicity in assigning a single numeric score for each input feature to a model. In the actionable recourse setting, wherein the goal of the explanations is to improve outcomes for model consumers, it is often unclear how feature attributions should be correctly used. With this work, we aim to strengthen and clarify the link between actionable recourse and feature attributions. Concretely, we propose a variant of SHAP, CoSHAP, that uses counterfactual generation techniques to produce a background dataset for use within the marginal (a.k.a. interventional) Shapley value framework. We motivate the need within the actionable recourse setting for careful consideration of background datasets when using Shapley values for feature attributions, alongside the requirement for monotonicity, with numerous synthetic examples. Moreover, we demonstrate the efficacy of CoSHAP by proposing and justifying a quantitative score for feature attributions, counterfactual-ability, showing that as measured by this metric, CoSHAP is superior to existing methods when evaluated on public datasets using monotone tree ensembles.

翻译：特性属性是模型解释的一个常见范例。 模型属性是一个典型的范例, 因为它们在为模型的每个输入特性指定一个单一的数值评分时简单。 在可操作的追索环境中, 解释的目的是改善模型消费者的结果, 通常不清楚特性属性应如何正确使用。 通过这项工作, 我们的目标是加强和澄清可操作的追索和特性属性之间的联系。 具体地说, 我们提议了一个 SHAP 的变式, 即 CoSHAP, 使用反事实生成技术来产生背景数据集, 供边际( a.k.a. 干涉性) 损耗值框架使用。 在可操作的追索设置中, 我们提出需要仔细考虑背景数据集, 在使用光谱值进行特性属性归属时, 以及要求单调性, 并举许多合成例子。 此外, 我们通过提出和证明CSHAP 的特性属性属性属性的定量评分, 反事实可操作性, 表明根据这一指标衡量, COSHAP 优于使用单质树 来评估公共数据集时的现有方法 。