{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/unbiased-measurement-of-feature-importance-in","title":"Unbiased Measurement of Feature Importance in Tree-Based Methods","arxiv_id":"1903.05179","date":"2019-03-12","proceeding":null,"authors":["Zhengze Zhou","Giles Hooker"],"abstract":"We propose a modification that corrects for split-improvement variable importance measures in Random Forests and other tree-based methods. These methods have been shown to be biased towards increasing the importance of features with more potential splits. We show that by appropriately incorporating split-improvement as measured on out of sample data, this bias can be corrected yielding better summaries and screening tools.","url_abs":"https://arxiv.org/abs/1903.05179v2","url_pdf":"https://arxiv.org/pdf/1903.05179v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"unbiased-measurement-of-feature-importance-in","repo_url":"https://github.com/ZhengzeZhou/unbiased-feature-importance","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"feature-importance","task_name":"Feature Importance"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.05179","atlas_url":"https://app.syntology.ai/?focus=1903.05179","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}