{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:24:25Z","timestamp":1778603065975,"version":"3.51.4"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100004071","name":"Khon Kaen University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004071","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"DOI":"10.1186\/s40537-024-00982-x","type":"journal-article","created":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T08:02:25Z","timestamp":1725264145000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["CTGAN-ENN: a tabular GAN-based hybrid sampling method for imbalanced and overlapped data in customer churn prediction"],"prefix":"10.1186","volume":"11","author":[{"given":"I Nyoman Mahayasa","family":"Adiputra","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paweena","family":"Wanchai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,2]]},"reference":[{"key":"982_CR1","doi-asserted-by":"publisher","first-page":"117998","DOI":"10.1016\/j.eswa.2022.117998","volume":"207","author":"X Wen","year":"2022","unstructured":"Wen X, Wang Y, Ji X, Traor\u00e9 MK. Three-stage churn management framework based on DCN with asymmetric loss. Expert Syst Appl. 2022;207:117998. https:\/\/doi.org\/10.1016\/j.eswa.2022.117998.","journal-title":"Expert Syst Appl"},{"key":"982_CR2","doi-asserted-by":"publisher","first-page":"1397","DOI":"10.1016\/j.ins.2022.07.145","volume":"609","author":"B Zhu","year":"2022","unstructured":"Zhu B, Pan X, Vanden Broucke S, Xiao J. A GAN-based hybrid sampling method for imbalanced customer classification. Inf Sci. 2022;609:1397\u2013411. https:\/\/doi.org\/10.1016\/j.ins.2022.07.145.","journal-title":"Inf Sci"},{"issue":"6","key":"982_CR3","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1109\/TAI.2022.3160658","volume":"3","author":"S Das","year":"2022","unstructured":"Das S, Mullick SS, Zelinka I. On supervised class-imbalanced learning: an updated perspective and some key challenges. IEEE Trans Artif Intell. 2022;3(6):973\u201393. https:\/\/doi.org\/10.1109\/TAI.2022.3160658.","journal-title":"IEEE Trans Artif Intell"},{"key":"982_CR4","unstructured":"Goodfellow IJ et al. Generative Adversarial Networks. 2014. http:\/\/arxiv.org\/abs\/1406.2661"},{"key":"982_CR5","volume-title":"Designing machine learning systems","author":"C Huyen","year":"2022","unstructured":"Huyen C. Designing machine learning systems. Sebastopol: O\u2019Reilly Media; 2022."},{"key":"982_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2022.102100","author":"L Geiler","year":"2022","unstructured":"Geiler L, Affeldt S, Nadif M. An effective strategy for churn prediction and customer profiling. Data Knowl Eng. 2022. https:\/\/doi.org\/10.1016\/j.datak.2022.102100.","journal-title":"Data Knowl Eng"},{"key":"982_CR7","doi-asserted-by":"publisher","first-page":"62118","DOI":"10.1109\/ACCESS.2021.3073776","volume":"9","author":"S Wu","year":"2021","unstructured":"Wu S, Yau W-C, Ong T-S, Chong S-C. Integrated churn prediction and customer segmentation framework for telco business. IEEE Access. 2021;9:62118\u201336. https:\/\/doi.org\/10.1109\/ACCESS.2021.3073776.","journal-title":"IEEE Access"},{"key":"982_CR8","doi-asserted-by":"publisher","unstructured":"Su C, Wei L, Xie X. Churn prediction in telecommunications industry based on conditional Wasserstein GAN, In: 2022 IEEE 29th International Conference on High Performance Computing, Data, and Analytics (HiPC), 2022, pp. 186\u2013191. https:\/\/doi.org\/10.1109\/HiPC56025.2022.00034.","DOI":"10.1109\/HiPC56025.2022.00034"},{"issue":"2","key":"982_CR9","doi-asserted-by":"publisher","first-page":"103235","DOI":"10.1016\/j.ipm.2022.103235","volume":"60","author":"H Ding","year":"2023","unstructured":"Ding H, Sun Y, Wang Z, Huang N, Shen Z, Cui X. RGAN-EL: a GAN and ensemble learning-based hybrid approach for imbalanced data classification. Inf Process Manag. 2023;60(2):103235. https:\/\/doi.org\/10.1016\/j.ipm.2022.103235.","journal-title":"Inf Process Manag"},{"key":"982_CR10","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1016\/j.ins.2014.08.051","volume":"291","author":"JA S\u00e1ez","year":"2015","unstructured":"S\u00e1ez JA, Luengo J, Stefanowski J, Herrera F. SMOTE-IPF: addressing the noisy and borderline examples problem in imbalanced classification by a re-sampling method with filtering. Inf Sci. 2015;291:184\u2013203. https:\/\/doi.org\/10.1016\/j.ins.2014.08.051.","journal-title":"Inf Sci"},{"key":"982_CR11","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.ins.2019.08.062","volume":"509","author":"P Vuttipittayamongkol","year":"2020","unstructured":"Vuttipittayamongkol P, Elyan E. Neighbourhood-based undersampling approach for handling imbalanced and overlapped data. Inf Sci. 2020;509:47\u201370. https:\/\/doi.org\/10.1016\/j.ins.2019.08.062.","journal-title":"Inf Sci"},{"key":"982_CR12","doi-asserted-by":"publisher","first-page":"103465","DOI":"10.1016\/j.jbi.2020.103465","volume":"107","author":"Z Xu","year":"2020","unstructured":"Xu Z, Shen D, Nie T, Kou Y. A hybrid sampling algorithm combining M-SMOTE and ENN based on random forest for medical imbalanced data. J Biomed Inform. 2020;107:103465. https:\/\/doi.org\/10.1016\/j.jbi.2020.103465.","journal-title":"J Biomed Inform"},{"key":"982_CR13","unstructured":"Elkan C. The Foundations of Cost-Sensitive Learning."},{"key":"982_CR14","volume-title":"LNCS 2888\u2014KNN model-based approach in classification","author":"G Guo","year":"2003","unstructured":"Guo G, Wang H, Bell D, Bi Y, Greer K. LNCS 2888\u2014KNN model-based approach in classification. Berlin: Springer; 2003."},{"issue":"4","key":"982_CR15","doi-asserted-by":"publisher","first-page":"953","DOI":"10.1007\/s12553-021-00550-w","volume":"11","author":"M Altuve","year":"2021","unstructured":"Altuve M, Alvarez AJ, Severeyn E. Multiclass classification of metabolic conditions using fasting plasma levels of glucose and insulin. Health Technol (Berl). 2021;11(4):953\u201362. https:\/\/doi.org\/10.1007\/s12553-021-00550-w.","journal-title":"Health Technol (Berl)"},{"key":"982_CR16","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.ijcce.2021.01.001","volume":"2","author":"S Kumari","year":"2021","unstructured":"Kumari S, Kumar D, Mittal M. An ensemble approach for classification and prediction of diabetes mellitus using soft voting classifier. Int J Cogn Comput Eng. 2021;2:40\u20136. https:\/\/doi.org\/10.1016\/j.ijcce.2021.01.001.","journal-title":"Int J Cogn Comput Eng"},{"key":"982_CR17","doi-asserted-by":"publisher","unstructured":"Chen T, Guestrin C. XGBoost: a scalable tree boosting system. 2016. https:\/\/doi.org\/10.1145\/2939672.2939785.","DOI":"10.1145\/2939672.2939785"},{"key":"982_CR18","unstructured":"Biau G, Fr GB. Analysis of a random forests model. 2012."},{"issue":"5","key":"982_CR19","doi-asserted-by":"publisher","first-page":"2727","DOI":"10.1007\/s10489-020-01997-6","volume":"51","author":"LK Shrivastav","year":"2021","unstructured":"Shrivastav LK, Jha SK. A gradient boosting machine learning approach in modeling the impact of temperature and humidity on the transmission rate of COVID-19 in India. Appl Intell. 2021;51(5):2727\u201339. https:\/\/doi.org\/10.1007\/s10489-020-01997-6.","journal-title":"Appl Intell"},{"key":"982_CR20","unstructured":"Ke G et al. LightGBM: A highly efficient gradient boosting decision tree. https:\/\/github.com\/Microsoft\/LightGBM. Accessed 17 Mar 2023."},{"key":"982_CR21","unstructured":"Xu L, Skoularidou M, Cuesta-Infante A, Veeramachaneni K. Modeling Tabular data using Conditional GAN. 2019. http:\/\/arxiv.org\/abs\/1907.00503. Accessed 8 May 2023."},{"key":"982_CR22","unstructured":"Telco Customer Churn | Kaggle. https:\/\/www.kaggle.com\/datasets\/blastchar\/telco-customer-churn. Accessed 07 Jun 2023."},{"key":"982_CR23","unstructured":"Churn Modelling | Kaggle. https:\/\/www.kaggle.com\/datasets\/shrutimechlearn\/churn-modelling. Accessed 07 Jun 2023."},{"key":"982_CR24","unstructured":"mobile-churn-data.xlsx | Kaggle. https:\/\/www.kaggle.com\/datasets\/dimitaryanev\/mobilechurndataxlsx. Accessed 07 Jun 2023"},{"key":"982_CR25","unstructured":"Customer Churn Prediction 2020 | Kaggle. https:\/\/www.kaggle.com\/competitions\/customer-churn-prediction-2020. Accessed 07 Jun 2023."},{"key":"982_CR26","unstructured":"Customer Churn. https:\/\/www.kaggle.com\/datasets\/royjafari\/customer-churn. Accessed 18 Mar 2024"},{"key":"982_CR27","unstructured":"Vinod Kumar. Insurance churn prediction\u202f: weekend hackathon. https:\/\/www.kaggle.com\/datasets\/k123vinod\/insurance-churn-prediction-weekend-hackathon. Accessed 15 Mar 2023."},{"key":"982_CR28","unstructured":"SMOTE\u2014Version 0.10.1. https:\/\/imbalanced-learn.org\/stable\/references\/generated\/imblearn.over_sampling.SMOTE.html. Accessed 08 Jun 2023."},{"issue":"17","key":"982_CR29","first-page":"1","volume":"18","author":"G Lema\u00eetre","year":"2017","unstructured":"Lema\u00eetre G, Nogueira F, Aridas CK. Imbalanced-learn: a python toolbox to tackle the curse of imbalanced datasets in machine learning. J Mach Learn Res. 2017;18(17):1\u20135.","journal-title":"J Mach Learn Res"},{"key":"982_CR30","unstructured":"ydata-synthetic Python package for synthetic data generation for tabular and time-series data. https:\/\/docs.synthetic.ydata.ai\/1.3\/. Accessed 04 Jul 2023."},{"key":"982_CR31","unstructured":"ctgan \u00b7 PyPI.https:\/\/pypi.org\/project\/ctgan\/. Accessed 08 Jun 2023."},{"key":"982_CR32","unstructured":"EditedNearestNeighbours\u2014Version 0.10.1. https:\/\/imbalanced-learn.org\/stable\/references\/generated\/imblearn.under_sampling.EditedNearestNeighbours.html. Accessed 08 Jun 2023."},{"key":"982_CR33","unstructured":"SMOTEENN\u2014Version 0.10.1. https:\/\/imbalanced-learn.org\/stable\/references\/generated\/imblearn.combine.SMOTEENN.html. Accessed 08 Jun 2023."},{"issue":"85","key":"982_CR34","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, et al. Scikit-learn: machine learning in python. J Mach Learn Res. 2011;12(85):2825\u201330.","journal-title":"J Mach Learn Res"},{"key":"982_CR35","unstructured":"XGBoost Documentation\u2014xgboost 2.0.3 documentation. https:\/\/xgboost.readthedocs.io\/en\/stable\/. Accessed 19 Mar 2024."},{"key":"982_CR36","unstructured":"sklearn.ensemble.RandomForestClassifier\u2014scikit-learn 1.4.1 documentation. https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.ensemble.RandomForestClassifier.html. Accessed 12 Mar 2024."},{"key":"982_CR37","unstructured":"lightgbm.LGBMClassifier\u2014LightGBM 4.3.0.99 documentation. https:\/\/lightgbm.readthedocs.io\/en\/latest\/pythonapi\/lightgbm.LGBMClassifier.html. Accessed 19 Mar 2024."}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-024-00982-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40537-024-00982-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-024-00982-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T08:07:04Z","timestamp":1725264424000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-024-00982-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,2]]},"references-count":37,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["982"],"URL":"https:\/\/doi.org\/10.1186\/s40537-024-00982-x","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3644024\/v1","asserted-by":"object"}]},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,2]]},"assertion":[{"value":"21 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that this research works have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"121"}}