---
title: "SHAP Analysis"
type: concept
tags: [interpretability, explainability, ml-ops]
sources: [specialized-model-qa]
last_updated: 2026-04-20
---

## Definition
SHAP（SHapley Additive exPlanations）是一种基于博弈论的模型可解释性方法，用于分解单个预测中每个特征的贡献。

## Outputs
- 全局解释：summary / beeswarm / bar plot
- 局部解释：waterfall / force plot
- 交互分析：SHAP interaction values

## Use in Model QA
- 解释预测驱动因素
- 检查特征贡献是否稳定
- 识别异常依赖或潜在偏差

## Related Concepts
- [[Partial Dependence Plots]]
- [[Model Audit]]