{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T16:10:10Z","timestamp":1791907810557,"version":"4.3.4"},"reference-count":44,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2021,1,4]],"date-time":"2021-01-04T00:00:00Z","timestamp":1609718400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"CCF Division of Computing and Communication Foundations","award":["TRIPODS 1740882"],"award-info":[{"award-number":["TRIPODS 1740882"]}]},{"DOI":"10.13039\/100000155","name":"Division Of Environmental Biology","doi-asserted-by":"crossref","award":["DEB-1353039"],"award-info":[{"award-number":["DEB-1353039"]}],"id":[{"id":"10.13039\/100000155","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000121","name":"Division of Mathematical Sciences","doi-asserted-by":"publisher","award":["DMS-1712554"],"award-info":[{"award-number":["DMS-1712554"]}],"id":[{"id":"10.13039\/100000121","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2021,4,30]]},"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.1145\/3429445","type":"journal-article","created":{"date-parts":[[2021,1,4]],"date-time":"2021-01-04T14:34:22Z","timestamp":1609770862000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":36,"title":["Unbiased Measurement of Feature Importance in Tree-Based Methods"],"prefix":"10.1145","volume":"15","author":[{"given":"Zhengze","family":"Zhou","sequence":"first","affiliation":[{"name":"Cornell University, Ithaca, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giles","family":"Hooker","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,1,4]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1214\/15-AOS1337"},{"key":"e_1_2_1_2_1","first-page":"392","article-title":"Book Review: Regression Diagnostics: Identifying Influential Data and Sources of Collinearity","volume":"18","author":"Bollinger Galen","year":"1981","journal-title":"Journal of Marketing Research"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbr053"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00058655"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_1_6_1","volume-title":"Stone","author":"Breiman Leo","year":"1984"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-5-132"},{"key":"e_1_2_1_9_1","volume-title":"Proceedings of the International Conference on Machine Learning. 665--673","author":"Denil Misha","year":"2014"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-7-3"},{"key":"e_1_2_1_11_1","volume-title":"The Elements of Statistical Learning","author":"Friedman Jerome"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"e_1_2_1_13_1","volume-title":"Boosting random forests to reduce bias","author":"Ghosal Indrayudh","year":"2020"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-016-9646-1"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1198\/106186007X237892"},{"key":"e_1_2_1_16_1","volume-title":"Please stop permuting features: An explanation and alternatives. arXiv preprint arXiv:1905.03151","author":"Hooker Giles","year":"2019"},{"key":"e_1_2_1_17_1","volume-title":"Party: A laboratory for recursive partytioning.","author":"Hothorn Torsten","year":"2010"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1198\/106186006X133933"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1214\/07-EJS039"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1214\/08-AOAS169"},{"key":"e_1_2_1_21_1","volume-title":"Predicting the direction of stock market prices using random forest. arXiv preprint arXiv:1605.00003","author":"Khaidem Luckyson","year":"2016"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1198\/016214501753168271"},{"key":"e_1_2_1_23_1","first-page":"8049","article-title":"A debiased MDI feature importance measure for random forests","volume":"32","author":"Li Xiao","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1214\/09-AOAS260"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1111\/insr.12016"},{"key":"e_1_2_1_26_1","first-page":"815","article-title":"Split selection methods for classification trees","volume":"7","author":"Loh Wei-Yin","year":"1997","journal-title":"Statistica Sinica"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946671"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-10-213"},{"key":"e_1_2_1_29_1","volume-title":"Siqi Liang, Robert Fragoza, Aaron Rumack, Jin Liang, Xiaomu Wei, and Haiyuan Yu.","author":"Meyer Michael","year":"2017"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty373"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbr016"},{"key":"e_1_2_1_32_1","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","author":"Pedregosa Fabian","year":"2011","journal-title":"Journal of Machine Learning Research 12"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50037-X"},{"key":"e_1_2_1_34_1","volume-title":"5: Programs for Machine Learning","author":"Quinlan J. Ross"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1198\/106186008X344522"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1214\/15-AOS1321"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2926725"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-9-307"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-8-25"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1319839"},{"key":"e_1_2_1_41_1","doi-asserted-by":"crossref","first-page":"3510","DOI":"10.1109\/TNNLS.2017.2729778","article-title":"A novel consistent random forest framework: Bernoulli random forests","volume":"29","author":"Wang Yisen","year":"2017","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_2_1_42_1","volume-title":"Proceedings of the IJCAI International Joint Conference on Artificial Intelligence.","author":"Yisen Wang","year":"2016"},{"key":"e_1_2_1_43_1","volume-title":"Boulevard: Regularized stochastic gradient boosted trees and their limiting distribution. arXiv preprint arXiv:1806.09762","author":"Zhou Yichen","year":"2018"},{"key":"e_1_2_1_44_1","volume-title":"Approximation trees: Statistical stability in model distillation. arXiv preprint arXiv:1808.07573","author":"Zhou Yichen","year":"2018"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3429445","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3429445","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3429445","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:03Z","timestamp":1750193283000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3429445"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,4]]},"references-count":44,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,4,30]]}},"alternative-id":["10.1145\/3429445"],"URL":"https:\/\/doi.org\/10.1145\/3429445","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,4]]},"assertion":[{"value":"2019-03-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-10-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-01-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}