用分组条件Shapley值解释模型预测变化原因
ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values
- 基于决策树结构定义数据子群，计算条件概率变化对预测的影响
- 可精确解释单棵树，扩展到集成模型并处理残差影响
- 适用于神经网络等模型，适合动态环境下的模型监控
输入分布的变化可能导致机器学习模型的平均预测发生偏移，进而影响下游业务结果（如银行贷款审批率）。我们提出 extit{ShapShift}：一种基于条件概率变化的分组条件Shapley值方法，用于将预测偏移归因于可解释子群的条件概率变化。该方法首先应用于单棵决策树，基于分裂节点的条件概率变化提供精确解释；接着扩展至树集成模型，通过选取最具解释力的树并考虑残差效应；最后提出一种模型无关变体，利用新型目标函数构建代理树，使方法可应用于神经网络等模型。尽管精确计算可能开销较大，但近似技术使其具备实际应用可行性。实验表明， extit{ShapShift}能为不同模型类型提供简洁、忠实且接近完整的预测偏移解释，有助于在动态环境中进行模型监控。
原文摘要 · Abstract (English)
Changes in input distribution can induce shifts in the average predictions of machine learning models. Such prediction shifts may impact downstream business outcomes (e.g. a bank's loan approval rate), so understanding their causes can be crucial. We propose \ours{}: a Shapley value method for attributing prediction shifts to changes in the conditional probabilities of interpretable subgroups of data, where these subgroups are defined by the structure of decision trees. We initially apply this method to single decision trees, providing exact explanations based on conditional probability changes at split nodes. Next, we extend it to tree ensembles by selecting the most explanatory tree and accounting for residual effects. Finally, we propose a model-agnostic variant using surrogate trees grown with a novel objective function, allowing application to models like neural networks. While exact computation can be intensive, approximation techniques enable practical application. We show that \ours{} provides simple, faithful, and near-complete explanations of prediction shifts across model classes, aiding model monitoring in dynamic environments.
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。