{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T12:12:11Z","timestamp":1778155931193,"version":"3.51.4"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032253071","type":"print"},{"value":"9783032253088","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-25308-8_9","type":"book-chapter","created":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T11:36:55Z","timestamp":1778153815000},"page":"130-145","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Bias-Aware Synthetic Data Generation: A\u00a0Tailored Use Case-Driven Approach"],"prefix":"10.1007","author":[{"given":"Barbara","family":"Draghi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Puja","family":"Myles","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Allan","family":"Tucker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,8]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Anahideh, H., Nezami, N., Asudeh, A.: Finding representative group fairness metrics using correlation estimations (2022)","DOI":"10.2139\/ssrn.4411805"},{"key":"9_CR2","doi-asserted-by":"publisher","unstructured":"Asudeh, A., Jin, Z., Jagadish, H.V.: Assessing and remedying coverage for a given dataset. In: 2019 IEEE 35th International Conference on Data Engineering (ICDE), pp. 554\u2013565 (2019). https:\/\/doi.org\/10.1109\/ICDE.2019.00056","DOI":"10.1109\/ICDE.2019.00056"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Breiman, L.: Random forests. Mach. Learn. 45, 5\u201332 (2001)","DOI":"10.1023\/A:1010933404324"},{"key":"9_CR4","unstructured":"van Breugel, B., Kyono, T., Berrevoets, J., van\u00a0der Schaar, M.: Decaf: generating fair synthetic data using causally-aware generative networks (2021)"},{"key":"9_CR5","unstructured":"Caton, S., Haas, C.: Fairness in machine learning: A survey (2020)"},{"key":"9_CR6","doi-asserted-by":"publisher","unstructured":"Chakraborty, J., Majumder, S., Menzies, T.: Bias in machine learning software: why? how? what to do? In: Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. ESEC\/FSE \u201921, ACM (2021). https:\/\/doi.org\/10.1145\/3468264.3468537","DOI":"10.1145\/3468264.3468537"},{"key":"9_CR7","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: Synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321\u2013357 (2002). https:\/\/doi.org\/10.1613\/jair.953","journal-title":"J. Artif. Intell. Res."},{"key":"9_CR8","doi-asserted-by":"publisher","unstructured":"Criscuolo, C., Dolci, T., Salnitri, M.: Towards Assessing Data Bias in Clinical Trials, pp. 57\u201374. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-23905-2_5","DOI":"10.1007\/978-3-031-23905-2_5"},{"key":"9_CR9","doi-asserted-by":"publisher","unstructured":"De-Arteaga, M., et al.: Bias in bios: A case study of semantic representation bias in a high-stakes setting. In: Proceedings of the Conference on Fairness, Accountability, and Transparency. ACM (2019). https:\/\/doi.org\/10.1145\/3287560.3287572","DOI":"10.1145\/3287560.3287572"},{"issue":"2","key":"9_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e24164","volume":"10","author":"B Draghi","year":"2024","unstructured":"Draghi, B., Wang, Z., Myles, P., Tucker, A.: Identifying and handling data bias within primary healthcare data using synthetic data generators. Heliyon 10(2), e24164 (2024). https:\/\/doi.org\/10.1016\/j.heliyon.2024.e24164","journal-title":"Heliyon"},{"key":"9_CR11","doi-asserted-by":"publisher","unstructured":"Emam, K., Mosquera, L., Fang, X., El-Hussuna, A.: An evaluation of the replicability of analyses using synthetic health data. Sci. Rep. 14 (2024). https:\/\/doi.org\/10.1038\/s41598-024-57207-7","DOI":"10.1038\/s41598-024-57207-7"},{"key":"9_CR12","doi-asserted-by":"publisher","unstructured":"Espinosa, E., Figueira, A.: On the quality of synthetic generated tabular data. Mathematics 11(15) (2023). https:\/\/doi.org\/10.3390\/math11153278","DOI":"10.3390\/math11153278"},{"key":"9_CR13","unstructured":"Ferrara, E.: Bias and fairness in ai: Systematic errors in decision-making processes. J. Artif. Intell. Res. (2020)"},{"issue":"3","key":"9_CR14","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1609\/aimag.v38i3.2741","volume":"38","author":"B Goodman","year":"2017","unstructured":"Goodman, B., Flaxman, S.: European union regulations on algorithmic decision-making and a \u2018right to explanation\u2019. AI Mag. 38(3), 50\u201357 (2017). https:\/\/doi.org\/10.1609\/aimag.v38i3.2741","journal-title":"AI Mag."},{"key":"9_CR15","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.neucom.2022.04.053","volume":"493","author":"M Hernandez","year":"2022","unstructured":"Hernandez, M., Epelde, G., Alberdi, A., Cilla, R., Rankin, D.: Synthetic data generation for tabular health records: a systematic review. Neurocomputing 493, 28\u201345 (2022). https:\/\/doi.org\/10.1016\/j.neucom.2022.04.053","journal-title":"Neurocomputing"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Hosmer\u00a0Jr, D.W., Lemeshow, S., Sturdivant, R.X.: Applied logistic regression. John Wiley & Sons (2013)","DOI":"10.1002\/9781118548387"},{"key":"9_CR17","unstructured":"Jordon, J., et al.: Synthetic data \u2013 what, why and how? (2022)"},{"key":"9_CR18","unstructured":"Loukas, O., Chung, H.R.: Demographic parity: mitigating biases in real-world data (2023)"},{"key":"9_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2023.100546","volume":"48","author":"H Murtaza","year":"2023","unstructured":"Murtaza, H., Ahmed, M., Khan, N.F., Murtaza, G., Zafar, S., Bano, A.: Synthetic data generation: state of the art in health care domain. Comput. Sci. Rev. 48, 100546 (2023). https:\/\/doi.org\/10.1016\/j.cosrev.2023.100546","journal-title":"Comput. Sci. Rev."},{"key":"9_CR20","unstructured":"Rish, I.: An empirical study of the na\u00efve bayes classifier. IJCAI 2001 Work Empir. Methods Artif. Intell. 3 (2001)"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Sayantan\u00a0Khanra, Amandeep\u00a0Dhir, A.K.M.N.I., M\u00e4ntym\u00e4ki, M.: Big data analytics in healthcare: a systematic literature review. Enterprise Inf. Syst. 14(7), 878\u2013912 (2020). 10.1080\/17517575.2020.1812005,","DOI":"10.1080\/17517575.2020.1812005"},{"issue":"13s","key":"9_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3588433","volume":"55","author":"N Shahbazi","year":"2023","unstructured":"Shahbazi, N., Lin, Y., Asudeh, A., Jagadish, H.V.: Representation bias in data: a survey on identification and resolution techniques. ACM Comput. Surv. 55(13s), 1\u201339 (2023). https:\/\/doi.org\/10.1145\/3588433","journal-title":"ACM Comput. Surv."},{"issue":"1","key":"9_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-020-00353-9","volume":"3","author":"A Tucker","year":"2020","unstructured":"Tucker, A., Wang, Z., Rotalinti, Y., Myles, P.: Generating high-fidelity synthetic patient data for assessing machine learning healthcare software. NPJ Digital Med. 3(1), 1\u201313 (2020)","journal-title":"NPJ Digital Med."},{"key":"9_CR24","doi-asserted-by":"publisher","unstructured":"Verma, S., Rubin, J.: Fairness definitions explained. In: 2018 IEEE\/ACM International Workshop on Software Fairness (FairWare), pp.\u00a01\u20137 (2018). https:\/\/doi.org\/10.1145\/3194770.3194776","DOI":"10.1145\/3194770.3194776"},{"key":"9_CR25","doi-asserted-by":"publisher","unstructured":"Wang, Z., Draghi, B., Rotalinti, Y., Lunn, D., Myles, P.: High-fidelity synthetic data applications for data augmentation. In: Dom\u00ednguez-Morales, M., Civit-Masot, J., Mu\u00f1oz-Saavedra, L., Dama\u0161evi\u010dius, R. (eds.) Deep Learning, chap.\u00a07. IntechOpen, Rijeka (2024). https:\/\/doi.org\/10.5772\/intechopen.113884","DOI":"10.5772\/intechopen.113884"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Z., Myles, P., Tucker, A.: Generating and evaluating synthetic UK primary care data: Preserving data utility & patient privacy. In: 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS), pp. 126\u2013131. IEEE (2019)","DOI":"10.1109\/CBMS.2019.00036"},{"issue":"6","key":"9_CR27","doi-asserted-by":"publisher","first-page":"1740","DOI":"10.1093\/ije\/dyz034","volume":"48","author":"A Wolf","year":"2019","unstructured":"Wolf, A., Dedman, D., Campbell, J., Booth, H., Lunn, D., Chapman, J., Myles, P.: Data resource profile: clinical practice research datalink (CPRD) aurum. Int. J. Epidemiol. 48(6), 1740\u20131740g (2019)","journal-title":"Int. J. Epidemiol."},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Xu, D., Yuan, S., Zhang, L., Wu, X.: Fairgan: fairness-aware generative adversarial networks (2018)","DOI":"10.24963\/ijcai.2019\/201"}],"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\/978-3-032-25308-8_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T11:37:09Z","timestamp":1778153829000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-25308-8_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032253071","9783032253088"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-25308-8_9","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"8 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"Vilnius","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}