A data scientist needs model-agnostic local explanations for individual predictions from a gradient boosting model. Which technique provides additive feature attributions that sum to the difference between the model's output and the global expected output?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — b is correct because SHAP values satisfy three game-theory axioms (local accuracy, missingness, consistency) and guarantee that each feature's contribution sums to the difference between the individual prediction and the global mean prediction. A (PDPs) show global average effects, not individual explanations.
Full explanation below image
Full Explanation
B is correct because SHAP values satisfy three game-theory axioms (local accuracy, missingness, consistency) and guarantee that each feature's contribution sums to the difference between the individual prediction and the global mean prediction. A (PDPs) show global average effects, not individual explanations. C (LIME) provides local linear approximations but does not sum to the exact prediction difference. D (variable importance) is a global metric, not a per-observation local explanation.