{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T04:58:37Z","timestamp":1768625917584,"version":"3.49.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031236174","type":"print"},{"value":"9783031236181","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-23618-1_28","type":"book-chapter","created":{"date-parts":[[2023,1,30]],"date-time":"2023-01-30T07:05:49Z","timestamp":1675062349000},"page":"418-433","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Are SHAP Values Biased Towards High-Entropy Features?"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6617-7894","authenticated-orcid":false,"given":"Raphael","family":"Baudeu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8542-6291","authenticated-orcid":false,"given":"Marvin N.","family":"Wright","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6823-1994","authenticated-orcid":false,"given":"Markus","family":"Loecher","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,1,31]]},"reference":[{"key":"28_CR1","unstructured":"Lundberg, S.M., Lee, S-I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems (2017)"},{"key":"28_CR2","doi-asserted-by":"publisher","unstructured":"Shapley, L.S.: A Value for N-Person Games, pp. 307\u2013318. Princeton University Press (2016). https:\/\/doi.org\/10.1515\/9781400881970-018","DOI":"10.1515\/9781400881970-018"},{"issue":"3","key":"28_CR3","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1007\/s10115-013-0679-x","volume":"41","author":"E \u0160trumbelj","year":"2014","unstructured":"\u0160trumbelj, E., Kononenko, I.: Explaining prediction models and individual predictions with feature contributions. Knowl. Inf. Syst. 41(3), 647\u2013665 (2014)","journal-title":"Knowl. Inf. Syst."},{"key":"28_CR4","unstructured":"Lundberg, S.M., Erion, G.G., Lee, S-I.: Consistent individualized feature attribution for tree ensembles. arXiv preprint arXiv:1802.03888 (2018)"},{"key":"28_CR5","unstructured":"Leo, B., Friedman, J.H., Olshen, R.A., Stone, C.J.: Classification and Regression Trees. CRC Press, Boca Raton (1984)"},{"issue":"1","key":"28_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-8-25","volume":"8","author":"C Strobl","year":"2007","unstructured":"Strobl, C., Boulesteix, A.-L., Zeileis, A., Hothorn, T.: Bias in random forest variable importance measures: illustrations, sources and a solution. BMC Bioinf. 8(1), 1\u201321 (2007)","journal-title":"BMC Bioinf."},{"issue":"3","key":"28_CR7","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1093\/bib\/bbr053","volume":"13","author":"AL Boulesteix","year":"2012","unstructured":"Boulesteix, A.L., Bender, A., Lorenzo Bermejo, J., Strobl, C.: Random forest GINI importance favours snps with large minor allele frequency: impact, sources and recommendations. Briefings Bioinf. 13(3), 292\u2013304 (2012)","journal-title":"Briefings Bioinf."},{"issue":"8","key":"28_CR8","doi-asserted-by":"publisher","first-page":"1272","DOI":"10.1002\/sim.7212","volume":"36","author":"MN Wright","year":"2017","unstructured":"Wright, M.N., Dankowski, T., Ziegler, A.: Unbiased split variable selection for random survival forests using maximally selected rank statistics. Stat. Med. 36(8), 1272\u20131284 (2017)","journal-title":"Stat. Med."},{"issue":"21","key":"28_CR9","doi-asserted-by":"publisher","first-page":"3711","DOI":"10.1093\/bioinformatics\/bty373","volume":"34","author":"S Nembrini","year":"2018","unstructured":"Nembrini, S., K\u00f6nig, I.R., Wright, M.N.: The revival of the GINI importance? Bioinformatics 34(21), 3711\u20133718 (2018)","journal-title":"Bioinformatics"},{"key":"28_CR10","unstructured":"Loecher, M.: From unbiased mdi feature importance to explainable AI for trees. arXiv preprint arXiv:2003.12043 (2020)"},{"key":"28_CR11","doi-asserted-by":"publisher","unstructured":"Loecher, M.: Debiasing MDI feature importance and SHAP values in tree ensembles. In: Holzinger, A., Kieseberg, P., Tjoa, A.M., Weippl, E. (eds.) Machine Learning and Knowledge Extraction. CD-MAKE 2022. Lecture Notes in Computer Science, vol. 13480, pp. 114\u2013129. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-14463-9_8","DOI":"10.1007\/978-3-031-14463-9_8"},{"issue":"5","key":"28_CR12","doi-asserted-by":"publisher","first-page":"687","DOI":"10.3390\/e24050687","volume":"24","author":"AI Adler","year":"2022","unstructured":"Adler, A.I., Painsky, A.: Feature importance in gradient boosting trees with cross-validation feature selection. Entropy 24(5), 687 (2022)","journal-title":"Entropy"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Molnar, C.: Interpretable machine learning (2019)","DOI":"10.21105\/joss.00786"},{"issue":"1","key":"28_CR14","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L.: Random forests. Mach. Learn. 45(1), 5\u201332 (2001)","journal-title":"Mach. Learn."},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Probst, P., Wright, M.N., Boulesteix, A.L.: Hyperparameters and tuning strategies for random forest. Wiley Interdisc. Rev. Data Min. Knowl. Disc. 9(3), e1301 (2019)","DOI":"10.1002\/widm.1301"},{"issue":"1","key":"28_CR16","first-page":"1934","volume":"20","author":"P Probst","year":"2019","unstructured":"Probst, P., Boulesteix, A.-L., Bischl, B.: Tunability: importance of hyperparameters of machine learning algorithms. J. Mach. Learn. Res. 20(1), 1934\u20131965 (2019)","journal-title":"J. Mach. Learn. Res."},{"key":"28_CR17","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/0095-0696(78)90006-2","volume":"5","author":"D Harrison","year":"1978","unstructured":"Harrison, D., Rubinfeld, D.: Hedonic housing prices and the demand for clean air. J. Environ. Econ. Manage. 5, 81\u2013102 (1978)","journal-title":"J. Environ. Econ. Manage."},{"issue":"3","key":"28_CR18","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1198\/106186006X133933","volume":"15","author":"T Hothorn","year":"2006","unstructured":"Hothorn, T., Hornik, K., Zeileis, A.: Unbiased recursive partitioning: a conditional inference framework. J. Comput. Graph. Stat. 15(3), 651\u2013674 (2006)","journal-title":"J. Comput. Graph. Stat."},{"key":"28_CR19","first-page":"07","volume":"7","author":"W-Y Loh","year":"1999","unstructured":"Loh, W.-Y., Shih, Y.: Split selection methods for classification trees. Stat. Sinica 7, 07 (1999)","journal-title":"Stat. Sinica"},{"issue":"5","key":"28_CR20","first-page":"1","volume":"51","author":"M Loecher","year":"2020","unstructured":"Loecher, M.: Unbiased variable importance for random forests. Commun. Stat. Theor. Methods 51(5), 1\u201313 (2020)","journal-title":"Commun. Stat. Theor. Methods"},{"key":"28_CR21","unstructured":"Covert, I., Lundberg, S.M., Lee, S-I.: In: Advances in Neural Information Processing Systems (2020)"},{"key":"28_CR22","first-page":"3533","volume":"34","author":"A Sutera","year":"2021","unstructured":"Sutera, A., Louppe, G., Huynh-Thu, V.A., Wehenkel, L., Geurts, P.: From global to local mdi variable importances for random forests and when they are shapley values. Adv. Neural Inf. Process. Syst. 34, 3533\u20133543 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"28_CR23","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1007\/978-3-030-10925-7_40","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"G Casalicchio","year":"2019","unstructured":"Casalicchio, G., Molnar, C., Bischl, B.: Visualizing the feature importance for black box models. In: Berlingerio, M., Bonchi, F., G\u00e4rtner, T., Hurley, N., Ifrim, G. (eds.) ECML PKDD 2018. LNCS (LNAI), vol. 11051, pp. 655\u2013670. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-10925-7_40"},{"key":"28_CR24","first-page":"1229","volume":"33","author":"C Frye","year":"2020","unstructured":"Frye, C., Rowat, C., Feige, I.: Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability. Adv. Neural Inf. Process. Syst. 33, 1229\u20131239 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"28_CR25","unstructured":"Williamson, B., Feng, J.: Efficient nonparametric statistical inference on population feature importance using Shapley values. In: International Conference on Machine Learning, pp. 10282\u201310291. PMLR (2020)"},{"key":"28_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/978-3-030-84060-0_19","volume-title":"Machine Learning and Knowledge Extraction","author":"A Yasodhara","year":"2021","unstructured":"Yasodhara, A., Asgarian, A., Huang, D., Sobhani, P.: On the trustworthiness of tree ensemble explainability methods. In: Holzinger, A., Kieseberg, P., Tjoa, A.M., Weippl, E. (eds.) CD-MAKE 2021. LNCS, vol. 12844, pp. 293\u2013308. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-84060-0_19"},{"key":"28_CR27","unstructured":"Alvarez-Melis, D., Jaakkola, T.S.: On the robustness of interpretability methods. arXiv preprint arXiv:1806.08049 (2018)"},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: Why should i trust you? explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135\u20131144 (2016)","DOI":"10.1145\/2939672.2939778"},{"key":"28_CR29","unstructured":"Chen, H., Janizek, J.D., Lundberg, S., Lee, S-I.: True to the model or true to the data? arXiv preprint arXiv:2006.16234 (2020)"}],"container-title":["Communications in Computer and Information Science","Machine Learning and Principles and Practice of Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-23618-1_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,30]],"date-time":"2023-01-30T07:14:34Z","timestamp":1675062874000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-23618-1_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031236174","9783031236181"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-23618-1_28","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"31 January 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Grenoble","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2022.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1060","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"236","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"22% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"17 demo track papers have been accepted from 28 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}