RePEcML & AI Methods
Feature Importance for Mixed Data
The article proposes a new method in machine learning that combines the conditional predictive impact framework with sequential knockoff sampling to better distinguish between marginal and conditional measures in feature importance.
Featured in No. 56 on 10 Jul 2024 · on release day
- Released
- 10 Jul 2024
- First featured
- No. 56 · 10 Jul 2024
- Published in
- Not yet, as far as Semantic Scholar knows
- Shares when featured
- 15
- Identifier
- RePEc:spr:alstar:v:108:y:2024:i:2:d:10.1007_s10182-023-00477-9
Citations and venue from Semantic Scholar (ODC-BY), refreshed weekly. Summary: Quant Letter (CC BY 4.0).