用自动化规则+少量人工修正，让AI解释更准更省力
Augmenting Intelligence: A Hybrid Framework for Scalable and Stable Explanations
- 用自动规则发现通用留客模式，再加人工补缺特定流失风险
- 仅需4条人工规则就达94%准确率，比全手动8规则还高
- 适合需要高效可解释AI的业务场景，降低专家工作量
当前可解释AI（XAI）面临“可扩展性-稳定性困境”：后处理方法（如LIME、SHAP）易扩展但不稳定，监督式解释框架（如TED）稳定但需为每个训练样本标注，人力成本过高。本文提出混合LRR-TED框架，通过“发现不对称性”解决此问题。在客户流失预测任务中，自动规则学习器（GLRM）擅长识别广泛的“安全网”（留存模式），但难以捕捉具体的“风险陷阱”（流失诱因），这一现象称为流失的安娜·卡列尼娜原则。通过用自动化安全规则初始化解释矩阵，并补充帕累托最优的4条人工定义风险规则，该方法实现94.00%的预测准确率。该配置优于完整的8规则人工基线，同时将人工标注工作量减少50%，推动人机协同AI范式转变：专家从“规则撰写者”转为“异常处理者”。
原文摘要 · Abstract (English)
Current approaches to Explainable AI (XAI) face a "Scalability-Stability Dilemma." Post-hoc methods (e.g., LIME, SHAP) may scale easily but suffer from instability, while supervised explanation frameworks (e.g., TED) offer stability but require prohibitive human effort to label every training instance. This paper proposes a Hybrid LRR-TED framework that addresses this dilemma through a novel "Asymmetry of Discovery." When applied to customer churn prediction, we demonstrate that automated rule learners (GLRM) excel at identifying broad "Safety Nets" (retention patterns) but struggle to capture specific "Risk Traps" (churn triggers)-a phenomenon we term the Anna Karenina Principle of Churn. By initialising the explanation matrix with automated safety rules and augmenting it with a Pareto-optimal set of just four human-defined risk rules, our approach achieves 94.00% predictive accuracy. This configuration outperforms the full 8-rule manual expert baseline while reducing human annotation effort by 50%, proposing a shift in the paradigm for Human-in-the-Loop AI: moving experts from the role of "Rule Writers" to "Exception Handlers."
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。