衡量信任的脆弱性：通过解释稳定性（CIES）设计可信度指数以支持商业决策系统
Measuring the Fragility of Trust: Devising Credibility Index via Explanation Stability (CIES) for Business Decision Support Systems
AI总结：
本文提出CIES指标，通过解释稳定性衡量AI模型解释的可信度，验证模型复杂度和数据平衡对解释稳定性的影响，为商业决策系统提供可信度预警。
摘要：
可解释人工智能（XAI）方法（如SHAP、LIME）越来越多地被采用以解释高风险业务中的模型。然而，这些解释的可信度，其在现实数据扰动下的稳定性，仍未被量化。本文介绍了通过解释稳定性设计的可信度指数（CIES），这是一个数学上站得住脚的度量标准，用于衡量模型在受现实商业噪声影响时解释的鲁棒性。CIES捕捉的是预测背后的原因是否保持一致，而不仅仅是预测本身。该指标采用一种排名加权距离函数，对最重要的特征的不稳定性施加不成比例的惩罚，反映了业务语义中，顶级决策驱动因素的变化比边缘特征的变化更具影响。我们评估了CIES在三个数据集（客户流失、信用风险、员工流失）、四种树分类模型和两种数据平衡条件下的表现。结果表明，模型复杂性影响解释可信度，通过SMOTE进行类别不平衡处理不仅影响预测性能，还影响解释稳定性，且CIES相比统一基线度量在统计上具有更优越的判别能力（所有24种配置中p < 0.同等的噪声水平下的敏感性分析确认了该指标本身的稳健性。这些发现为业务从业者提供了一个可部署的“可信度警告系统”以支持AI驱动的决策。
英文摘要：
Explainable Artificial Intelligence (XAI) methods (SHAP, LIME) are increasingly adopted to interpret models in high-stakes businesses. However, the credibility of these explanations, their stability under realistic data perturbations, remains unquantified. This paper introduces the Credibility Index via Explanation Stability (CIES), a mathematically grounded metric that measures how robust a model's explanations are when subject to realistic business noise. CIES captures whether the reasons behind a prediction remain consistent, not just the prediction itself. The metric employs a rank-weighted distance function that penalizes instability in the most important features disproportionately, reflecting business semantics where changes in top decision drivers are more consequential than changes in marginal features. We evaluate CIES across three datasets (customer churn, credit risk, employee attrition), four tree-based classification models and two data balancing conditions. Results demonstrate that model complexity impacts explanation credibility, class imbalance treatment via SMOTE affects not only predictive performance but also explanation stability, and CIES provides statistically superior discriminative power compared to a uniform baseline metric (p < 0.01 in all 24 configurations). A sensitivity analysis across four noise levels confirms the robustness of the metric itself. These findings offer business practitioners a deployable "credibility warning system" for AI-driven decision support.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
