{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T12:52:34Z","timestamp":1781959954751,"version":"3.54.5"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"Ningbo Science and Technology (S&T) Bureau","award":["2021B-008-C"],"award-info":[{"award-number":["2021B-008-C"]}]},{"DOI":"10.13039\/501100021178","name":"University of Nottingham Ningbo China","doi-asserted-by":"publisher","award":["LDS202307"],"award-info":[{"award-number":["LDS202307"]}],"id":[{"id":"10.13039\/501100021178","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Substantial financial losses due to fraud drive the need for accurate detection algorithms. However, machine learning classifiers frequently show bias towards non-fraudulent classes due to class imbalance, where fraudulent instances occur much less frequently. Current oversampling techniques, such as the Synthetic Minority Oversampling TEchnique and Generative Adversarial Networks, generate noisy samples, produce suboptimal proportions of minority classes, and neglect majority class distributions, leading to degraded classifier performance. To address these limitations, this study investigates the feasibility of reinforcement learning (RL) for selecting generated minority samples. This study proposes a general-purpose RL-based sample selection method that is agnostic to both oversampling technique and classifier, which dynamically filters the generated minority samples using classifier feedback and information from minority and majority neighborhoods. The investigation reveals technical challenges, including sparse reward and high computational cost, which must be addressed for RL to become a practical solution for minority sample selection.<\/jats:p>","DOI":"10.1093\/comjnl\/bxag011","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T12:38:21Z","timestamp":1768394301000},"page":"1069-1079","source":"Crossref","is-referenced-by-count":0,"title":["Minority sample selection in fraud detection with classifier-based reinforcement learning"],"prefix":"10.1093","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8067-423X","authenticated-orcid":false,"given":"Patience Chew Yee","family":"Cheah","sequence":"first","affiliation":[{"name":"School of Computer Science, University of Nottingham Ningbo China , 199 Taikang East Road, University Park, Ningbo, 315100 Zhejiang ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5743-1010","authenticated-orcid":false,"given":"Boon Giin","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Nottingham Ningbo China , 199 Taikang East Road, University Park, Ningbo, 315100 Zhejiang ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5755-5395","authenticated-orcid":false,"given":"Yue","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Nottingham Ningbo China , 199 Taikang East Road, University Park, Ningbo, 315100 Zhejiang ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"key":"2026062008163992900_ref1","article-title":"Year-over-year developments in financial fraud detection via deep learning: a systematic literature review","author":"Chen","year":"2025"},{"key":"2026062008163992900_ref2","doi-asserted-by":"crossref","first-page":"116429","DOI":"10.1016\/j.eswa.2021.116429","article-title":"Financial fraud: a review of anomaly detection techniques and recent advances","volume":"193","author":"Waleed Hilal","year":"2022","journal-title":"Expert Syst Appl"},{"key":"2026062008163992900_ref3","article-title":"Credit card fraud detection","year":"2018","journal-title":"Kaggle"},{"key":"2026062008163992900_ref4","doi-asserted-by":"crossref","first-page":"110415","DOI":"10.1016\/j.asoc.2023.110415","article-title":"A broad review on class imbalance learning techniques","volume":"143","author":"Rezvani","year":"2023","journal-title":"Appl Soft Comput"},{"key":"2026062008163992900_ref5","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1007\/s10994-025-06755-8","article-title":"DatRel: a noise-tolerant data relocation approach for effective synthetic data generation in imbalanced classifiers","volume":"114","author":"Sa\u011flam","year":"2025","journal-title":"Mach Learn"},{"key":"2026062008163992900_ref6","doi-asserted-by":"crossref","first-page":"114582","DOI":"10.1016\/j.eswa.2021.114582","article-title":"Conditional Wasserstein GAN-based oversampling of tabular data for imbalanced learning","volume":"174","author":"Engelmann","year":"2021","journal-title":"Expert Syst Appl"},{"key":"2026062008163992900_ref7","first-page":"348","article-title":"Learning with limited minority class data","volume-title":"Proceedings of the 6th International Conference on Machine Learning and Applications (ICMLA)","author":"Khoshgoftaar","year":"2007"},{"key":"2026062008163992900_ref8","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1016\/j.ins.2017.12.030","article-title":"Using generative adversarial networks for improving classification effectiveness in credit card fraud detection","volume":"479","author":"Fiore","year":"2019","journal-title":"Inform Sci"},{"key":"2026062008163992900_ref9","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1186\/s40537-022-00648-6","article-title":"The use of generative adversarial networks to alleviate class imbalance in tabular data: A survey","volume":"9","author":"Sauber-Cole","year":"2022","journal-title":"Journal of Big Data"},{"key":"2026062008163992900_ref10","first-page":"511","article-title":"A computationally efficient density-aware adversarial resampling framework using wasserstein gans for imbalance and overlapping data classification","volume":"144","author":"Jubair","year":"2025","journal-title":"Comput Model Eng Sci"},{"key":"2026062008163992900_ref11","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1145\/1007730.1007735","article-title":"A study of the behavior of several methods for balancing machine learning training data","volume":"6","author":"Batista","year":"2004","journal-title":"ACM SIGKDD Explorations Newsletter"},{"key":"2026062008163992900_ref12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/CCECE53047.2021.9569056","article-title":"Reinforcement learning algorithms: An overview and classification","volume-title":"Proceedings of the 2021 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","author":"AlMahamid","year":"2021"},{"key":"2026062008163992900_ref13","first-page":"4707","article-title":"Trainable undersampling for class-imbalance learning","volume-title":"Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI)","author":"Peng","year":"2019"},{"key":"2026062008163992900_ref14","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J Artif Intell Res"},{"key":"2026062008163992900_ref15","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems (NIPS)","author":"Goodfellow","year":"2014"},{"key":"2026062008163992900_ref16","doi-asserted-by":"crossref","first-page":"9637","DOI":"10.3390\/app12199637","article-title":"Financial fraud detection based on machine learning: a systematic literature review","volume":"12","author":"Ali","year":"2022","journal-title":"Appl Sci"},{"key":"2026062008163992900_ref17","article-title":"Modeling tabular data using conditional GAN","volume-title":"Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS)","author":"Xu","year":"2019"},{"key":"2026062008163992900_ref18","doi-asserted-by":"crossref","first-page":"30655","DOI":"10.1109\/ACCESS.2022.3158977","article-title":"SMOTified-GAN for class imbalanced pattern classification problems","volume":"10","author":"Sharma","year":"2022","journal-title":"IEEE Access"},{"key":"2026062008163992900_ref19","article-title":"Synthetic data generation for fraud detection using gans","author":"Charitou","year":"2021"},{"key":"2026062008163992900_ref20","doi-asserted-by":"crossref","first-page":"120495","DOI":"10.1016\/j.eswa.2023.120495","article-title":"Reinforcement learning algorithms: a brief survey","volume":"231","author":"Shakya","year":"2023","journal-title":"Expert Syst Appl"},{"key":"2026062008163992900_ref21","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"2026062008163992900_ref22","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"2026062008163992900_ref23","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1109\/ICDM50108.2020.00016","article-title":"Learning to undersampling for class imbalanced credit risk forecasting","volume-title":"Proceedings of the 2020 IEEE International Conference on Data Mining (ICDM)","author":"Chi","year":"2020"},{"key":"2026062008163992900_ref24","doi-asserted-by":"crossref","first-page":"2518","DOI":"10.1109\/TII.2021.3100284","article-title":"Imbalanced sample selection with deep reinforcement learning for fault diagnosis","volume":"18","author":"Fan","year":"2022","journal-title":"IEEE Trans Industr Inform"},{"key":"2026062008163992900_ref25","first-page":"2476","article-title":"Towards automated imbalanced learning with deep hierarchical reinforcement learning","volume-title":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management (CIKM)","author":"Zha","year":"2022"},{"key":"2026062008163992900_ref26","doi-asserted-by":"crossref","first-page":"2488","DOI":"10.1007\/s10489-020-01637-z","article-title":"Deep reinforcement learning for imbalanced classification","volume":"50","author":"Lin","year":"2020","journal-title":"Applied Intelligence"},{"key":"2026062008163992900_ref27","article-title":"Application of deep reinforcement learning to payment fraud","author":"Vimal","year":"2021"},{"key":"2026062008163992900_ref28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/GCAT55367.2022.9972092","article-title":"A comparative study of supervised and reinforcement learning techniques for the application of credit defaulters","volume-title":"Proceedings of the 2022 IEEE 3rd Global Conference for Advancement in Technology (GCAT)","author":"Jacob","year":"2022"},{"key":"2026062008163992900_ref29","first-page":"1","article-title":"Intelligent fault quantitative identification via the improved deep deterministic policy gradient (ddpg) algorithm accompanied with imbalanced sample","volume":"72","author":"Cui","year":"2023","journal-title":"IEEE Trans Instrum Meas"},{"key":"2026062008163992900_ref30","first-page":"47","article-title":"Combining data resampling and drl algorithm for intrusion detection","volume-title":"Proceedings of the 5th International Conference on Computer Communication and the Internet (ICCCI)","author":"Su","year":"2023"},{"key":"2026062008163992900_ref31","doi-asserted-by":"crossref","first-page":"114101","DOI":"10.1016\/j.knosys.2025.114101","article-title":"DMRL: a distributed multi-agent reinforcement learning algorithm for imbalanced classification","volume":"327","author":"Ji","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"2026062008163992900_ref32","doi-asserted-by":"crossref","first-page":"23482","DOI":"10.1109\/ACCESS.2025.3536479","article-title":"Efficient handling of data imbalance in health insurance fraud detection using meta-reinforcement learning","volume":"13","author":"Seshagiri","year":"2025","journal-title":"IEEE Access"},{"key":"2026062008163992900_ref33","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1109\/TNSE.2020.3004312","article-title":"AESMOTE: adversarial reinforcement learning with SMOTE for anomaly detection","volume":"8","author":"Ma","year":"2021","journal-title":"IEEE Trans Netw Sci Eng"},{"key":"2026062008163992900_ref34","doi-asserted-by":"publisher","DOI":"10.24432\/C55S3H","article-title":"Default of credit card clients","author":"Yeh","year":"2016","journal-title":"UCI Machine Learning Repository"},{"key":"2026062008163992900_ref35","doi-asserted-by":"crossref","DOI":"10.52202\/068431-0037","article-title":"Why do tree-based models still outperform deep learning on typical tabular data?","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems (NeurIPS)","author":"Grinsztajn","year":"2022"},{"key":"2026062008163992900_ref36","first-page":"785","article-title":"Xgboost: A scalable tree boosting system","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)","author":"Chen","year":"2016"},{"key":"2026062008163992900_ref37","first-page":"878","article-title":"Borderline-smote: a new over-sampling method in imbalanced data sets learning","volume-title":"Proceedings of the 10th International Conference on Intelligent Computing (ICIC)","author":"Han","year":"2005"},{"key":"2026062008163992900_ref38","first-page":"1322","article-title":"Adasyn: Adaptive synthetic sampling approach for imbalanced learning","volume-title":"Proceedings of the 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)","author":"He","year":"2008"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/69\/6\/1069\/66641048\/bxag011.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/69\/6\/1069\/66641048\/bxag011.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T12:16:49Z","timestamp":1781957809000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/69\/6\/1069\/8445451"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,30]]},"references-count":38,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,1,30]]},"published-print":{"date-parts":[[2026,6,20]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxag011","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,6]]},"published":{"date-parts":[[2026,1,30]]}}}