{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T05:53:08Z","timestamp":1776405188908,"version":"3.51.2"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032238320","type":"print"},{"value":"9783032238337","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\/978-3-032-23833-7_23","type":"book-chapter","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T05:11:34Z","timestamp":1776402694000},"page":"312-326","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CARTGen-IR: Synthetic Tabular Data Generation for\u00a0Imbalanced Regression"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2205-6265","authenticated-orcid":false,"given":"Ant\u00f3nio Pedro","family":"Pinheiro","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6852-8077","authenticated-orcid":false,"given":"Rita P.","family":"Ribeiro","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,4,18]]},"reference":[{"key":"23_CR1","doi-asserted-by":"publisher","DOI":"10.2196\/55118","volume":"12","author":"I Akiya","year":"2024","unstructured":"Akiya, I., Ishihara, T., Yamamoto, K.: Comparison of synthetic data generation techniques for control group survival data in oncology clinical trials: simulation study. JMIR Med. Inform. 12, e55118 (2024)","journal-title":"JMIR Med. Inform."},{"key":"23_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2022.113220","volume":"281","author":"E Alerskans","year":"2022","unstructured":"Alerskans, E., Zinck, A., Nielsen-Englyst, P., H\u00f8yer, J.: Exploring machine learning techniques to retrieve sea surface temperatures from passive microwave measurements. Remote Sens. Environ. 281, 113220 (2022)","journal-title":"Remote Sens. Environ."},{"key":"23_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124118","volume":"252","author":"S Belhaouari","year":"2024","unstructured":"Belhaouari, S., Islam, A., Kassoul, K., Al-Fuqaha, A., Bouzerdoum, A.: Oversampling techniques for imbalanced data in regression. Expert Syst. Appl. 252, 124118 (2024)","journal-title":"Expert Syst. Appl."},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Branco, P., Torgo, L., Ribeiro, R.: A survey of predictive modeling on imbalanced domains. ACM Comput. Surv. 49, Article 31 (2016)","DOI":"10.1145\/2907070"},{"key":"23_CR5","unstructured":"Branco, P., Torgo, L., Ribeiro, R.: SMOGN: a pre-processing approach for imbalanced regression. In: Proceedings of the 1st International Workshop on Learning with Imbalanced Domains: Theory and Applications, pp. 36\u201350 (2017)"},{"key":"23_CR6","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.neucom.2018.11.100","volume":"343","author":"P Branco","year":"2019","unstructured":"Branco, P., Torgo, L., Ribeiro, R.: Pre-processing approaches for imbalanced distributions in regression. Neurocomputing 343, 76\u201399 (2019)","journal-title":"Neurocomputing"},{"key":"23_CR7","unstructured":"Branco, P., Tulon, S.: imbalance-metrics: a Python package for evaluating imbalanced datasets. Version 0.1.6, available via PyPI (2025)"},{"key":"23_CR8","volume-title":"Classification and Regression Trees","author":"L Breiman","year":"1984","unstructured":"Breiman, L., Friedman, J., Olshen, R., Stone, C.: Classification and Regression Trees. Chapman, New York (1984)"},{"issue":"1","key":"23_CR9","first-page":"27","volume":"3","author":"G Caiola","year":"2010","unstructured":"Caiola, G., Reiter, J.P.: Random forests for generating partially synthetic. Categorical Data. Trans. Data Privacy 3(1), 27\u201342 (2010)","journal-title":"Categorical Data. Trans. Data Privacy"},{"key":"23_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116387","volume":"193","author":"L Camacho","year":"2022","unstructured":"Camacho, L., Douzas, G., Bacao, F.: Geometric SMOTE for regression. Expert Syst. Appl. 193, 116387 (2022)","journal-title":"Expert Syst. Appl."},{"key":"23_CR11","doi-asserted-by":"publisher","first-page":"8789","DOI":"10.1007\/s10489-024-05608-6","volume":"54","author":"L Camacho","year":"2024","unstructured":"Camacho, L., Bacao, F.: WSMOTER: a novel approach for imbalanced regression. Appl. Intell. 54, 8789\u20138799 (2024)","journal-title":"Appl. Intell."},{"key":"23_CR12","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"N Chawla","year":"2002","unstructured":"Chawla, N., Bowyer, K., Hall, L., Kegelmeyer, W.: SMOTE: Synthetic Minority Over-sampling Technique. JAIR 16, 321\u2013357 (2002)","journal-title":"JAIR"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"He, H., Bai, Y., Garcia, E., Li, S.: ADASYN: Adaptive synthetic sampling approach for imbalanced learning. In: IEEE International Joint Conference on Neural Networks, pp. 1322\u20131328 (2008)","DOI":"10.1109\/IJCNN.2008.4633969"},{"key":"23_CR14","doi-asserted-by":"publisher","first-page":"5186","DOI":"10.1016\/j.csda.2007.11.008","volume":"52","author":"M Hubert","year":"2008","unstructured":"Hubert, M., Vandervieren, E.: An adjusted boxplot for skewed distributions. Comput. Stat. Data Anal. 52, 5186\u20135201 (2008)","journal-title":"Comput. Stat. Data Anal."},{"key":"23_CR15","unstructured":"Kotelnikov, A., Baranchuk, D., Rubachev, I., Babenko, A.: TabDDPM: modelling tabular data with diffusion models. In: Proceedings of the 40th International Conference on Machine Learning (ICML\u201923), Article No. 725, pp. 1\u201316 (2023)"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Lenhof, K., Eckhart, L., Gerstner, N., Kehl, T., Lenhof, H.: Simultaneous regression and classification for drug sensitivity prediction using an advanced random forest method. Sci. Rep. 12 (2022)","DOI":"10.1038\/s41598-022-17609-x"},{"key":"23_CR17","doi-asserted-by":"publisher","first-page":"375","DOI":"10.3390\/pr12020375","volume":"12","author":"X Liu","year":"2024","unstructured":"Liu, X., Tian, H.: Research on imbalanced data regression based on confrontation. Processes 12, 375 (2024)","journal-title":"Processes"},{"key":"23_CR18","unstructured":"Panagiotou, E., Roy, A., Ntoutsi, E.: Synthetic tabular data generation for class imbalance and fairness: a comparative study. arXiv:2409.05215 (2024)"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Patki, N., Wedge, R., Veeramachaneni, K.: The synthetic data vault. In: 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA), pp. 399\u2013410 (2016)","DOI":"10.1109\/DSAA.2016.49"},{"key":"23_CR20","unstructured":"Reiter, J.: Using CART to generate partially synthetic, public use microdata. J. Official Stat. 21 (2005)"},{"key":"23_CR21","unstructured":"Ribeiro, R.: Utility-based Regression. Faculty of Sciences, University of Porto, Department of Computer Science (2011)"},{"key":"23_CR22","doi-asserted-by":"publisher","first-page":"1803","DOI":"10.1007\/s10994-020-05900-9","volume":"109","author":"R Ribeiro","year":"2020","unstructured":"Ribeiro, R., Moniz, N.: Imbalanced regression and extreme value prediction. Mach. Learn. 109, 1803\u20131835 (2020)","journal-title":"Mach. Learn."},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Schultz, M., et al.: Can deep learning beat numerical weather prediction?. Philos. Trans. Roy. Soc. Math. Phys. Eng. Sci. 379 (2021)","DOI":"10.1098\/rsta.2020.0097"},{"key":"23_CR24","doi-asserted-by":"publisher","first-page":"2187","DOI":"10.1007\/s10994-021-06023-5","volume":"110","author":"M Steininger","year":"2021","unstructured":"Steininger, M., Kobs, K., Davidson, P., Krause, A., Hotho, A.: Density-based weighting for imbalanced regression. Mach. Learn. 110, 2187\u20132211 (2021)","journal-title":"Mach. Learn."},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Stocksieker, S., Pommeret, D., Charpentier, A.: Data augmentation with variational autoencoder for imbalanced dataset. arXiv preprint arXiv:2412.07039 (2024)","DOI":"10.1007\/978-981-96-6579-2_24"},{"key":"23_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119157","volume":"642","author":"H Tian","year":"2023","unstructured":"Tian, H., Tian, C., Li, K., Jia, W.: Unbalanced regression sample generation algorithm based on confrontation. Inf. Sci. 642, 119157 (2023)","journal-title":"Inf. Sci."},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Torgo, L., Ribeiro, R., Pfahringer, B., Branco, P.: SMOTE for regression. In: Progress in Artificial Intelligence, pp. 378\u2013389 (2013)","DOI":"10.1007\/978-3-642-40669-0_33"},{"key":"23_CR28","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1111\/exsy.12081","volume":"32","author":"L Torgo","year":"2015","unstructured":"Torgo, L., Branco, P., Ribeiro, R., Pfahringer, B.: Resampling strategies for regression. Expert. Syst. 32, 465\u2013476 (2015)","journal-title":"Expert. Syst."},{"key":"23_CR29","unstructured":"Xu, L., Skoularidou, M., Cuesta-Infante, A., Veeramachaneni, K.: Modeling tabular data using conditional GAN. arXiv preprint arXiv:1907.00503 (2019)"}],"container-title":["Lecture Notes in Computer Science","Advances in Intelligent Data Analysis XXIV"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-23833-7_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T05:11:43Z","timestamp":1776402703000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-23833-7_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032238320","9783032238337"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-23833-7_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"18 April 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":"IDA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Intelligent Data Analysis","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Leiden","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 April 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 April 2026","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":"ida2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ida2026.liacs.nl\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}