{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T22:32:44Z","timestamp":1771021964177,"version":"3.50.1"},"reference-count":46,"publisher":"World Scientific Pub Co Pte Ltd","issue":"03","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Artif. Intell. Tools"],"published-print":{"date-parts":[[2024,5]]},"abstract":"<jats:p> Rising acceptance of machine learning driven decision support systems underscores the need for ensuring fairness for all stakeholders. This work proposes a novel approach to increase a Neural Network model\u2019s fairness during the training phase. We offer a frame-work to create a family of diverse fairness enhancing regularization components that can be used in tandem with the widely accepted binary-cross-entropy based accuracy loss. We use Bias Parity Score (BPS), a metric that quantifies model bias with a single value, to build loss functions pertaining to different statistical measures \u2014 even for those that may not be developed yet. We analyze behavior and impact of the newly minted regularization components on bias. We explore their impact in the realm of recidivism and census-based adult income prediction. The results illustrate that apt fairness loss functions can mitigate bias without forsaking accuracy even for imbalanced datasets. <\/jats:p>","DOI":"10.1142\/s0218213024600030","type":"journal-article","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T03:52:22Z","timestamp":1713930742000},"source":"Crossref","is-referenced-by-count":1,"title":["Fairness for Deep Learning Predictions Using Bias Parity Score Based Loss Function Regularization"],"prefix":"10.1142","volume":"33","author":[{"given":"Bhanu","family":"Jain","sequence":"first","affiliation":[{"name":"The University of Texas at Arlington, 500 UTA Blvd., Arlington, TX 76019, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manfred","family":"Huber","sequence":"additional","affiliation":[{"name":"The University of Texas at Arlington, 500 UTA Blvd., Arlington, TX 76019, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ramez","family":"Elmasri","sequence":"additional","affiliation":[{"name":"The University of Texas at Arlington, 500 UTA Blvd., Arlington, TX 76019, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2024,4,25]]},"reference":[{"key":"S0218213024600030BIB002","doi-asserted-by":"publisher","DOI":"10.1145\/3389189.3397990"},{"key":"S0218213024600030BIB003","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aao5580"},{"key":"S0218213024600030BIB004","doi-asserted-by":"publisher","DOI":"10.1287\/isre.2018.0789"},{"key":"S0218213024600030BIB005","doi-asserted-by":"publisher","DOI":"10.1002\/asmb.2455"},{"key":"S0218213024600030BIB006","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.02.026"},{"key":"S0218213024600030BIB007","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2018.3763"},{"key":"S0218213024600030BIB008","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2006.07.007"},{"key":"S0218213024600030BIB009","doi-asserted-by":"publisher","DOI":"10.1145\/3378393.3402507"},{"key":"S0218213024600030BIB010","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314277"},{"key":"S0218213024600030BIB011","unstructured":"M. Feldman,  Computational Fairness: Preventing Machine-learned Discrimination Senior Thesis (Bryn Mawr University,  2015)."},{"key":"S0218213024600030BIB012","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206819"},{"key":"S0218213024600030BIB013","first-page":"325","volume-title":"Int. Conf. on Machine Learning","author":"Zemel R.","year":"2013"},{"key":"S0218213024600030BIB014","doi-asserted-by":"publisher","DOI":"10.1145\/3316782.3322787"},{"key":"S0218213024600030BIB015","volume-title":"And it\u2019s biased against blacks","author":"Angwin J.","year":"2016"},{"key":"S0218213024600030BIB016","doi-asserted-by":"publisher","DOI":"10.1145\/3194770.3194776"},{"key":"S0218213024600030BIB017","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0047"},{"key":"S0218213024600030BIB018","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Zhao H.","year":"2019"},{"key":"S0218213024600030BIB019","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2009.83"},{"key":"S0218213024600030BIB022","first-page":"3315","volume-title":"Advances in Neural Information Processing Systems","author":"Hardt M.","year":"2016"},{"key":"S0218213024600030BIB023","doi-asserted-by":"publisher","DOI":"10.3390\/technologies8040068"},{"key":"S0218213024600030BIB024","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-010-0190-x"},{"key":"S0218213024600030BIB026","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186133"},{"key":"S0218213024600030BIB027","volume-title":"Adverse Impact and Test Validation: A Practitioner\u2019s Guide to Valid and Defensible Employment Testing","author":"Biddle D.","year":"2006"},{"key":"S0218213024600030BIB029","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783311"},{"key":"S0218213024600030BIB031","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1356"},{"key":"S0218213024600030BIB032","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287586"},{"key":"S0218213024600030BIB033","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052660"},{"key":"S0218213024600030BIB034","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-61527-7_11"},{"key":"S0218213024600030BIB035","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445902"},{"key":"S0218213024600030BIB037","first-page":"671","volume":"104","author":"Barocas S.","year":"2016","journal-title":"Calif. L. Rev"},{"key":"S0218213024600030BIB038","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2013.114"},{"key":"S0218213024600030BIB039","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462614"},{"key":"S0218213024600030BIB040","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445913"},{"key":"S0218213024600030BIB043","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00203"},{"key":"S0218213024600030BIB044","first-page":"702","volume-title":"Int. Conf. on Artificial Intelligence and Statistics","author":"Jiang H.","year":"2020"},{"key":"S0218213024600030BIB045","doi-asserted-by":"publisher","DOI":"10.1111\/rssa.12227"},{"key":"S0218213024600030BIB046","unstructured":"T. Ozkan,  Predicting Recidivism Through Machine Learning, PhD thesis (University of Texas at Dallas,  Dallas, TX,  2017)."},{"key":"S0218213024600030BIB048","doi-asserted-by":"publisher","DOI":"10.1177\/0193841X14531415"},{"key":"S0218213024600030BIB049","unstructured":"B. Jain,  Machine Learning Methods to Improve Fairness and Prediction Accuracy on Largesocially Relevant Datasets, PhD thesis (The University of Texas at Arlington,  Arlington, TX,  2021)."},{"key":"S0218213024600030BIB051","first-page":"202","volume-title":"Knowledge Discovery and Data Mining","author":"Kohavi R.","year":"1996"},{"issue":"1","key":"S0218213024600030BIB053","first-page":"1929","volume":"15","author":"Srivastava N.","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"S0218213024600030BIB054","first-page":"2483","volume-title":"Advances in Neural Information Processing Systems","author":"Santurkar S.","year":"2018"},{"key":"S0218213024600030BIB056","volume":"34","author":"Du M.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"S0218213024600030BIB057","volume":"34","author":"Gong C.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"S0218213024600030BIB059","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278779"},{"key":"S0218213024600030BIB061","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33486-3_3"}],"container-title":["International Journal on Artificial Intelligence Tools"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218213024600030","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,4]],"date-time":"2024-05-04T05:56:16Z","timestamp":1714802176000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0218213024600030"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,25]]},"references-count":46,"journal-issue":{"issue":"03","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["10.1142\/S0218213024600030"],"URL":"https:\/\/doi.org\/10.1142\/s0218213024600030","relation":{},"ISSN":["0218-2130","1793-6349"],"issn-type":[{"value":"0218-2130","type":"print"},{"value":"1793-6349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,25]]},"article-number":"2460003"}}