{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,18]],"date-time":"2026-11-18T18:29:06Z","timestamp":1795026546692,"version":"4.10.2"},"reference-count":82,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2023,5,27]],"date-time":"2023-05-27T00:00:00Z","timestamp":1685145600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"EPIC: Evolutionary Program Improvement Collaborators","award":["741278"],"award-info":[{"award-number":["741278"]}]},{"name":"UKRI Trustworthy Autonomous Systems Node in Verifiability","award":["EP\/V026801\/2"],"award-info":[{"award-number":["EP\/V026801\/2"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2023,10,31]]},"abstract":"<jats:p>Software bias is an increasingly important operational concern for software engineers. We present a large-scale, comprehensive empirical study of 17 representative bias mitigation methods for Machine Learning (ML) classifiers, evaluated with 11 ML performance metrics (e.g., accuracy), 4 fairness metrics, and 20 types of fairness-performance tradeoff assessment, applied to 8 widely-adopted software decision tasks. The empirical coverage is much more comprehensive, covering the largest numbers of bias mitigation methods, evaluation metrics, and fairness-performance tradeoff measures compared to previous work on this important software property. We find that (1) the bias mitigation methods significantly decrease ML performance in 53% of the studied scenarios (ranging between 42%\u223c66% according to different ML performance metrics); (2) the bias mitigation methods significantly improve fairness measured by the 4 used metrics in 46% of all the scenarios (ranging between 24%\u223c59% according to different fairness metrics); (3) the bias mitigation methods even lead to decrease in both fairness and ML performance in 25% of the scenarios; (4) the effectiveness of the bias mitigation methods depends on tasks, models, the choice of protected attributes, and the set of metrics used to assess fairness and ML performance; (5) there is no bias mitigation method that can achieve the best tradeoff in all the scenarios. The best method that we find outperforms other methods in 30% of the scenarios. Researchers and practitioners need to choose the bias mitigation method best suited to their intended application scenario(s).<\/jats:p>","DOI":"10.1145\/3583561","type":"journal-article","created":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T08:48:04Z","timestamp":1675932484000},"page":"1-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":96,"title":["A Comprehensive Empirical Study of Bias Mitigation Methods for Machine Learning Classifiers"],"prefix":"10.1145","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4765-1893","authenticated-orcid":false,"given":"Zhenpeng","family":"Chen","sequence":"first","affiliation":[{"name":"University College London"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0481-7264","authenticated-orcid":false,"given":"Jie M.","family":"Zhang","sequence":"additional","affiliation":[{"name":"King\u2019s College London"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9146-442X","authenticated-orcid":false,"given":"Federica","family":"Sarro","sequence":"additional","affiliation":[{"name":"University College London"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5864-4488","authenticated-orcid":false,"given":"Mark","family":"Harman","sequence":"additional","affiliation":[{"name":"University College London"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,5,27]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"The Adult Census Income dataset. Retrieved September 20 2021 from https:\/\/archive.ics.uci.edu\/ml\/datasets\/adult."},{"key":"e_1_3_2_3_2","unstructured":"Applications of scikit-learn. Retrieved November 24 2022 from https:\/\/numfocus.org\/project\/scikit-learn#::text=Implementations%20rely%20either%20on%20vectorized to%20analyzing%20brain%20imaging%20data."},{"key":"e_1_3_2_4_2","unstructured":"The Bank dataset. Retrieved September 20 2021 from https:\/\/archive.ics.uci.edu\/ml\/datasets\/Bank+Marketing."},{"key":"e_1_3_2_5_2","unstructured":"The Compas dataset. Retrieved September 20 2021 from https:\/\/github.com\/propublica\/compas-analysis."},{"key":"e_1_3_2_6_2","unstructured":"FATE: Fairness Accountability Transparency and Ethics in AI. Retrieved September 20 2021 fromhttps:\/\/www.microsoft.com\/en-us\/research\/theme\/fate\/."},{"key":"e_1_3_2_7_2","unstructured":"The German Credit dataset. Retrieved September 20 2021 fromhttps:\/\/archive.ics.uci.edu\/ml\/datasets\/Statlog+%28German+Credit+Data%29."},{"key":"e_1_3_2_8_2","unstructured":"The GitHub repository of Fair-SMOTE. Retrieved September 20 2021 fromhttps:\/\/github.com\/joymallyac\/Fair-SMOTE\/tree\/master\/Fair-SMOTE."},{"key":"e_1_3_2_9_2","unstructured":"The GitHub repository of Fairway. Retrieved September 20 2021 fromhttps:\/\/github.com\/joymallyac\/Fairway."},{"key":"e_1_3_2_10_2","unstructured":"IBM AI Fairness 360. Retrieved September 20 2021 fromhttps:\/\/aif360.mybluemix.net."},{"key":"e_1_3_2_11_2","unstructured":"Machine Bias. Retrieved September 20 2021 fromhttps:\/\/www.propublica.org\/article\/machine-bias-risk-assessments-in-criminal-sentencing."},{"key":"e_1_3_2_12_2","unstructured":"The Mep dataset. Retrieved September 20 2021 fromhttps:\/\/meps.ahrq.gov\/mepsweb\/data_stats\/download_data_files_detail.jsp?cboPufNumber=HC-181."},{"key":"e_1_3_2_13_2","unstructured":"Microsoft AI principles. Retrieved September 20 2021 fromhttps:\/\/www.microsoft.com\/en-us\/ai\/responsible-ai?activetab=pivot1%3aprimaryr6."},{"key":"e_1_3_2_14_2","unstructured":"Review into bias in algorithmic decision-making. Retrieved November 24 2022 fromhttps:\/\/www.gov.uk\/government\/publications\/cdei-publishes-review-into-bias-in-algorithmic-decision-making\/main-report-cdei-review-into-bias-in-algorithmic-decision-making."},{"key":"e_1_3_2_15_2","unstructured":"Scikit-learn. Retrieved September 20 2021 fromhttps:\/\/scikit-learn.org."},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aal4230"},{"key":"e_1_3_2_17_2","unstructured":"Study finds gender and skin-type bias in commercial artificial-intelligence systems. Retrieved September 20 2021 fromhttps:\/\/news.mit.edu\/2018\/study-finds-gender-skin-type-bias-artificial-intelligence-systems-0212."},{"key":"e_1_3_2_18_2","unstructured":"When good algorithms go sexist: Why and how to advance AI gender equity. Retrieved September 20 2021 fromhttps:\/\/ssir.org\/articles\/entry\/when_good_algorithms_go_sexist_why_and_how_to_advance_ai_gender_equity."},{"key":"e_1_3_2_19_2","unstructured":"Who is using scikit-learn?Retrieved November 24 2022 fromhttps:\/\/scikit-learn.org\/stable\/testimonials\/testimonials.html#id8."},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3338906.3338937"},{"key":"e_1_3_2_21_2","first-page":"158","volume-title":"Proceedings of the International Conference on Information and Communication Technology and Applications","author":"Alabi Kayode Omotosho","year":"2020","unstructured":"Kayode Omotosho Alabi, Sulaiman Olaniyi Abdulsalam, Roseline Oluwaseun Ogundokun, and Micheal Olaolu Arowolo. 2020. Credit risk prediction in commercial bank using chi-square with SVM-RBF. In Proceedings of the International Conference on Information and Communication Technology and Applications. 158\u2013169."},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/1985793.1985795"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1177\/0049124118782533"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409704"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468536"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00125812"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3264838"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2009.83"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-010-0190-x"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287586"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468537"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409697"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3418932"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3338906.3338977"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3424308"},{"key":"e_1_3_2_36_2","unstructured":"Zhenpeng Chen Jie M. Zhang Max Hort Federica Sarro and Mark Harman. 2022. Fairness testing: A comprehensive survey and analysis of trends. arXiv:2207.10223. Retrieved from https:\/\/arxiv.org\/abs\/2207.10223."},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549093"},{"key":"e_1_3_2_38_2","unstructured":"Zhenpeng Chen Jie M. Zhang Federica Sarro and Mark Harman. 2023. Replication package. Retrieved January 14 2023 from https:\/\/github.com\/chenzhenpeng18\/TOSEM23-BiasMitigationStudy."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-019-6413-7"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0047"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.4324\/9780203771587"},{"key":"e_1_3_2_42_2","first-page":"3992","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems 2017","author":"Calmon Fl\u00e1vio du Pin","year":"2017","unstructured":"Fl\u00e1vio du Pin Calmon, Dennis Wei, Bhanukiran Vinzamuri, Karthikeyan Natesan Ramamurthy, and Kush R. Varshney. 2017. Optimized pre-processing for discrimination prevention. In Proceedings of the Annual Conference on Neural Information Processing Systems 2017. 3992\u20134001."},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783311"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783311"},{"key":"e_1_3_2_45_2","first-page":"115","volume-title":"Proceedings of the 16th IEEE International Requirements Engineering Conference","author":"Finkelstein Anthony","year":"2008","unstructured":"Anthony Finkelstein, Mark Harman, Afshin Mansouri, Jian Ren, and Yuanyuan Zhang. 2008. Fairness analysis in requirements assignments. In Proceedings of the 16th IEEE International Requirements Engineering Conference. 115\u2013124."},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3106237.3106277"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1177\/0093854820969753"},{"key":"e_1_3_2_48_2","first-page":"3315","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems 2016","author":"Hardt Moritz","year":"2016","unstructured":"Moritz Hardt, Eric Price, and Nati Srebro. 2016. Equality of opportunity in supervised learning. In Proceedings of the Annual Conference on Neural Information Processing Systems 2016. 3315\u20133323."},{"key":"e_1_3_2_49_2","doi-asserted-by":"crossref","unstructured":"Max Hort Zhenpeng Chen Jie M. Zhang Federica Sarro and Mark Harman. 2022. Bias mitigation for machine learning classifiers: A comprehensive survey. arXiv:2207.07068. Retrieved from https:\/\/arxiv.org\/abs\/2207.07068.","DOI":"10.1145\/3631326"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678568"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468565"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-011-0463-8"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.50"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2012.45"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.09.064"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33486-3_3"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1057\/palgrave.rpm.5170078"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177730491"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3457607"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544902.3546255"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.4324\/9780203726631"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3379597.3387446"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3196398.3196403"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3494672"},{"key":"e_1_3_2_65_2","first-page":"5680","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems 2017","author":"Pleiss Geoff","year":"2017","unstructured":"Geoff Pleiss, Manish Raghavan, Felix Wu, Jon M. Kleinberg, and Kilian Q. Weinberger. 2017. On fairness and calibration. In Proceedings of the Annual Conference on Neural Information Processing Systems 2017. 5680\u20135689."},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/2601248.2601294"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-021-00592-x"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.22237\/jmasm\/1257035100"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/505282.505283"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220046"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2020.3048991"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238165"},{"key":"e_1_3_2_73_2","first-page":"8780","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems 2019","author":"Wick Michael L.","year":"2019","unstructured":"Michael L. Wick, Swetasudha Panda, and Jean-Baptiste Tristan. 2019. Unlocking fairness: A trade-off revisited. In Proceedings of the Annual Conference on Neural Information Processing Systems 2019. 8780\u20138789."},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3383219.3383232"},{"key":"e_1_3_2_75_2","first-page":"962","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics","author":"Zafar Muhammad Bilal","year":"2017","unstructured":"Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez-Rodriguez, and Krishna P. Gummadi. 2017. Fairness constraints: Mechanisms for fair classification. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics. 962\u2013970."},{"key":"e_1_3_2_76_2","first-page":"325","volume-title":"Proceedings of the 30th International Conference on Machine Learning","author":"Zemel Richard S.","year":"2013","unstructured":"Richard S. Zemel, Yu Wu, Kevin Swersky, Toniann Pitassi, and Cynthia Dwork. 2013. Learning fair representations. In Proceedings of the 30th International Conference on Machine Learning. 325\u2013333."},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278779"},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00129"},{"key":"e_1_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2019.2962027"},{"key":"e_1_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.1145\/3460319.3464820"},{"key":"e_1_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549103"},{"key":"e_1_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380331"},{"key":"e_1_3_2_83_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510123"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583561","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3583561","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T12:37:54Z","timestamp":1750163874000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583561"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,27]]},"references-count":82,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,10,31]]}},"alternative-id":["10.1145\/3583561"],"URL":"https:\/\/doi.org\/10.1145\/3583561","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,27]]},"assertion":[{"value":"2022-01-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-01-11","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}