KernelSHAP vs TreeSHAP

Comparing SHAP approximation methods based on speed, complexity and other considerations

(source: flaticon)

Both KernelSHAP and TreeSHAP are used to approximate Shapley values. TreeSHAP is much faster. The downside is that it can only be used with tree-based algorithms like random forests and xgboost. On the other hand, KernelSHAP is model agnostic. This means it can be used with any…