用响应度评分提升模型解释的可操作性，让用户知道哪些改变能真正改变结果。
Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse
- 根据特征可改变性计算响应度，而非仅依赖重要性排序
- 传统方法可能推荐无法改变的结果，误导用户决策
- 适用于信贷等高风险场景，帮助用户找到真实可行的改善路径
在高风险决策中，消费者保护法规要求企业向受影响个体解释预测依据。这一要求部分基于解释能促进可救济性的假设——即个体可据此采取行动改变结果。目前企业多采用SHAP、LIME等方法，基于特征重要性生成主要原因列表。本文指出，此类实践可能失效：某些被强调的特征实际上不可干预，或预测结果固定不变。为此，我们提出基于响应度（responsiveness）的解释框架——衡量个体通过任意干预某特征实现目标预测的概率。我们开发了适用于任意模型与可操作性约束的高效计算方法。实证表明，传统做法可能误导用户，而响应度评分能更有效地揭示真正可改变的特征，支持实际救济。
原文摘要 · Abstract (English)
Consumer protection rules require companies that deploy models to automate decisions in high-stakes settings to explain predictions to decision subjects. These rules are motivated, in part, by the belief that explanations can promote recourse by revealing information that decision subjects can use to contest or overturn their predictions. In practice, companies provide individuals with a list of principal reasons based on feature importance derived from methods like SHAP and LIME. In this work, we show how common practices can fail to provide recourse and propose to highlight features based on their responsiveness -- the probability that a decision subject can attain a target prediction through an arbitrary intervention on the feature. We develop efficient methods to compute responsiveness scores for any model and actionability constraints. We show that standard practices in lending can undermine decision subjects by highlighting unresponsive features and explaining predictions that are fixed.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。