EasyDeepLearn

Can you use SHAP values for feature selection?

medium

Answer

  • Yes — mean absolute SHAP value across a validation sample gives a robust, model-consistent importance ranking.
  • Advantages over impurity: unbiased for cardinality, respects the model's actual behavior, works per-example.
  • Practical selection: sort by mean  SHAP\mathrm{mean}\; \mid \mathrm{SHAP}|, keep features that together explain a target fraction (e.g., 95%) of total absolute SHAP, or drop features below a floor threshold.
  • Downside: computing SHAP is more expensive than impurity, and highly correlated features share importance in ways that can be misleading.
Check yourself — multiple choice
  • SHAP can only be used for classification
  • Rank by mean  SHAP  on\mathrm{mean}\; \mid \mathrm{SHAP} \mid \;\mathrm{on} validation; drop features below a threshold or below cumulative-share cutoff
  • SHAP is unrelated to feature importance
  • SHAP requires linear models

Mean  SHAP\mathrm{Mean}\; \mid \mathrm{SHAP}| = robust importance; select by threshold or cumulative-share cutoff.

#feature-selection#interpretability

Practise Supervised Learning

215 interview questions in this topic.

Related questions