SHAP: SHapley Additive exPlanations

[emptymalei]

SHAP (SHapley Additive exPlanations) is a system of interpreting machine learning models.
The author of SHAP built an easy-to-use package to help us understand how the features are contributing to the machine learning model predictions. The package comes with a comprehensive tutorial for different machine learning frameworks.

• Python Package: slundberg/shap

---

The package is so popular and you might be using it already. So what is SHAP exactly? It is a system of methods based on Shapley values.

SHAP (SHapley Additive exPlanations) is a game-theoretic approach to explain the output of any machine learning model.

-- slundberg/shap

Regarding Shapley value: There are two key ideas in calculating a Shapley value.

• A method to measure the contribution to the final prediction of features.
• A method to combine these "contributions" into a score.

SHAP provides more methods to estimate Shapley values and also for different models.

The following two pages explain Shapley value and SHAP thoroughly.

• https://christophm.github.io/interpretable-ml-book/shap.html
• https://christophm.github.io/interpretable-ml-book/shapley.html

---

I posted a similar article years ago in our data weekly newsletter.