{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:37:40Z","timestamp":1775745460331,"version":"3.50.1"},"reference-count":41,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>Credit card fraud remains a major cause of financial loss around the world. Traditional fraud detection methods that rely on supervised learning often struggle because fraudulent transactions are rare compared to legitimate ones, leading to imbalanced datasets. Additionally, the models must be retrained frequently, as fraud patterns change over time and require new labeled data for retraining. To address these challenges, this paper proposes an ensemble unsupervised learning approach for credit card fraud detection that combines Autoencoders (AEs), Self-Organizing Maps (SOMs), and Restricted Boltzmann Machines (RBMs), integrated with an Adaptive Reconstruction Threshold (ART) mechanism. The ART dynamically adjusts anomaly detection thresholds by leveraging the clustering properties of SOMs, effectively overcoming the limitations of static threshold approaches in machine learning and deep learning models. The proposed models, AE-ASOMs (Autoencoder\u2014Adaptive Self-Organizing Maps) and RBM-ASOMs (Restricted Boltzmann Machines\u2014Adaptive Self-Organizing Maps), were evaluated on the Kaggle Credit Card Fraud Detection and IEEE-CIS datasets. Our AE-ASOM model achieved an accuracy of 0.980 and an F1-score of 0.967, while the RBM-ASOM model achieved an accuracy of 0.975 and an F1-score of 0.955. Compared to models such as One-Class SVM and Isolation Forest, our approach demonstrates higher detection accuracy and significantly reduces false positive rates. In addition to its performance, the model offers considerable computational efficiency with a training time of 200.52 s and memory usage of 3.02 megabytes.<\/jats:p>","DOI":"10.3390\/bdcc9090217","type":"journal-article","created":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T08:53:46Z","timestamp":1756112026000},"page":"217","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["An Adaptive Unsupervised Learning Approach for Credit Card Fraud Detection"],"prefix":"10.3390","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6133-6092","authenticated-orcid":false,"given":"John","family":"Adejoh","sequence":"first","affiliation":[{"name":"Department of Software Engineering, African University of Science and Technology, Abuja 900107, Nigeria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4840-9345","authenticated-orcid":false,"given":"Nsikak","family":"Owoh","sequence":"additional","affiliation":[{"name":"Department of Cyber Security and Networks, Glasgow Caledonian University, Glasgow G4 0BA, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1016-0791","authenticated-orcid":false,"given":"Moses","family":"Ashawa","sequence":"additional","affiliation":[{"name":"Department of Cyber Security and Networks, Glasgow Caledonian University, Glasgow G4 0BA, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6253-5287","authenticated-orcid":false,"given":"Salaheddin","family":"Hosseinzadeh","sequence":"additional","affiliation":[{"name":"Department of Cyber Security and Networks, Glasgow Caledonian University, Glasgow G4 0BA, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6583-0617","authenticated-orcid":false,"given":"Alireza","family":"Shahrabi","sequence":"additional","affiliation":[{"name":"Department of Cyber Security and Networks, Glasgow Caledonian University, Glasgow G4 0BA, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Salma","family":"Mohamed","sequence":"additional","affiliation":[{"name":"Department of Cyber Security and Networks, Glasgow Caledonian University, Glasgow G4 0BA, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,25]]},"reference":[{"key":"ref_1","unstructured":"ACI-Worldwide (2025, January 02). Protect Your Customers, Reputation and Bottom Line. Available online: https:\/\/www.aciworldwide.com\/card-fraud-management."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"269","DOI":"10.30574\/gscarr.2025.22.3.0086","article-title":"The Role of AI in preventing financial fraud and enhancing compliance","volume":"22","author":"Adejumo","year":"2025","journal-title":"GSC Adv. Res. Rev."},{"key":"ref_3","first-page":"325","article-title":"Class balancing framework for credit card fraud detection based on clustering and similarity-based selection (SBS)","volume":"15","author":"Ahmad","year":"2023","journal-title":"Int. J. Inf. Technol."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Ahmed, K.R., Ansari, M.E., Ahsan, M.N., Rohan, A., Uddin, M.B., and Rivin, M.A.H. (2025). Deep learning framework for interpretable supply chain forecasting using SOM ANN and SHAP. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-11510-z"},{"key":"ref_5","first-page":"210","article-title":"Credit Card Fraud Detection Using an Autoencoder Model with New Loss Function","volume":"17","author":"Sulaiman","year":"2024","journal-title":"Int. J. Intell. Eng. Syst."},{"key":"ref_6","unstructured":"Rodr\u00edguez Vaquero, P. (2023). Literature Review of Credit Card Fraud Detection with Machine Learning. [Master\u2019s Thesis, Tampere University]."},{"key":"ref_7","unstructured":"Liu, W., Zeng, W., He, K., Jiang, Y., and He, J. (2023). What makes good data for alignment? a comprehensive study of automatic data selection in instruction tuning. arXiv."},{"key":"ref_8","unstructured":"Buzzard, J. (2025, January 30). Identity Fraud Study: The Virtual Battleground. Available online: https:\/\/javelinstrategy.com\/2022-Identity-fraud-scams-report."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"7","DOI":"10.37458\/ssj.4.1.1","article-title":"Terrorist and non-terrorist threats to European security","volume":"4","author":"Schmid","year":"2023","journal-title":"Secur. Sci. J."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"116624","DOI":"10.1016\/j.eswa.2022.116624","article-title":"A two-stage hybrid credit risk prediction model based on XGBoost and graph-based deep neural network","volume":"195","author":"Liu","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"30628","DOI":"10.1109\/ACCESS.2023.3262020","article-title":"A Deep Learning Ensemble with Data Resampling for Credit Card Fraud Detection","volume":"11","author":"Mienye","year":"2023","journal-title":"IEEE Access"},{"key":"ref_12","first-page":"74","article-title":"Advances in Neural Network for Credit Card Fraud Detection","volume":"15","author":"Singh","year":"2025","journal-title":"IJSAT-Int. J. Sci. Technol."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Khatri, S., Arora, A., and Agrawal, A.P. (2020, January 29\u201331). Supervised Machine Learning Algorithms for Credit Card Fraud Detection: A Comparison. Proceedings of the 2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence), Noida, India.","DOI":"10.1109\/Confluence47617.2020.9057851"},{"key":"ref_14","unstructured":"Felt, G.S. (2024). Predicting Loan Default with XGBoost: An Examination of Strength and Application. [Master\u2019s Thesis, University of Tartu]. Online."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Khalid, A.R., Owoh, N., Uthmani, O., Ashawa, M., Osamor, J., and Adejoh, J. (2024). Enhancing credit card fraud detection: An ensemble machine learning approach. Big Data Cogn. Comput., 8.","DOI":"10.3390\/bdcc8010006"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"942","DOI":"10.30574\/wjarr.2024.22.2.1455","article-title":"Machine learning for credit risk analysis across the United States","volume":"22","author":"Yufenyuy","year":"2024","journal-title":"World J. Adv. Res. Rev."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Jiang, S., Dong, R., Wang, J., and Xia, M. (2023). Credit card fraud detection based on unsupervised attentional anomaly detection network. Systems, 11.","DOI":"10.3390\/systems11060305"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Rai, A.K., and Dwivedi, R.K. (2020, January 28\u201330). Fraud Detection in Credit Card Data Using Unsupervised Machine Learning Based Scheme. Proceedings of the 2020 International Conference on Electronics and Sustainable Communication Systems (ICESC), Coimbatore, India.","DOI":"10.1109\/ICESC48915.2020.9155615"},{"key":"ref_19","unstructured":"Alvarez, M., Verdier, J.-C., Nkashama, D.J.K., Frappier, M., Tardif, P.M., and Kabanza, F. (2022). A Revealing Large-Scale Evaluation of Unsupervised Anomaly Detection Algorithms. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"119562","DOI":"10.1016\/j.eswa.2023.119562","article-title":"A novel combined approach based on deep Autoencoder and deep classifiers for credit card fraud detection","volume":"217","author":"Fanai","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/j.ins.2019.05.042","article-title":"Combining unsupervised and supervised learning in credit card fraud detection","volume":"557","author":"Carcillo","year":"2021","journal-title":"Inf. Sci."},{"key":"ref_22","unstructured":"Kyriienko, O., and Magnusson, E.B. (2022). Unsupervised quantum machine learning for fraud detection. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"202","DOI":"10.4114\/intartif.vol26iss72pp202-222","article-title":"An intelligent approach for anomaly detection in credit card data using bat optimization algorithm","volume":"26","author":"Sikkandar","year":"2023","journal-title":"Intel. Artif."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"865","DOI":"10.3103\/S0146411622080223","article-title":"Bank Fraud Detection with Graph Neural Networks","volume":"56","author":"Sergadeeva","year":"2022","journal-title":"Autom. Control Comput. Sci."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1186\/s40537-024-01041-1","article-title":"A problem-agnostic approach to feature selection and analysis using shap","volume":"12","author":"Hancock","year":"2025","journal-title":"J. Big Data"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"337","DOI":"10.37896\/YMER21.06\/32","article-title":"Credit Card Fraud Detection using Autoencoders","volume":"21","author":"Senthilvel","year":"2022","journal-title":"YMER"},{"key":"ref_27","first-page":"1","article-title":"Anomaly detection using unsupervised methods: Credit card fraud case study","volume":"10","author":"Rezapour","year":"2019","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.14445\/22312803\/IJCTT-V69I8P101","article-title":"Credit card fraud detection using unsupervised machine learning algorithms","volume":"69","author":"Hariteja","year":"2021","journal-title":"Int. J. Comput. Trends Technol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.51983\/ajeat-2022.11.2.3348","article-title":"Utilizing Prediction Intervals for Unsupervised Detection of Fraudulent Transactions: A Case Study","volume":"11","author":"Hewapathirana","year":"2022","journal-title":"Asian J. Eng. Technol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"175829","DOI":"10.1109\/ACCESS.2024.3502542","article-title":"A Hybrid Deep Learning Ensemble Model for Credit Card Fraud Detection","volume":"12","author":"Ileberi","year":"2024","journal-title":"IEEE Access"},{"key":"ref_31","first-page":"170","article-title":"Enhancing Retail Fraud Detection with Isolation Forests and Autoencoders: Overcoming Data limitations and Regulatory Challenges","volume":"3","author":"Thakre","year":"2024","journal-title":"J. Adv. Res. Eng. Technol."},{"key":"ref_32","unstructured":"Kaggle (2024, November 10). Credit Card Fraud Detection Dataset. Available online: https:\/\/www.kaggle.com\/datasets\/mlg-ulb\/creditcardfraud."},{"key":"ref_33","unstructured":"IEEE-CIS (2024, November 15). IEEE-CIS Fraud Detection Dataset. Available online: https:\/\/www.kaggle.com\/c\/ieee-fraud-detection."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Najadat, H., Altiti, O., Aqouleh, A.A., and Younes, M. (2020, January 7\u20139). Credit card fraud detection based on machine and deep learning. Proceedings of the 2020 11th International Conference on Information and Communication Systems (ICICS), Irbid, Jordan.","DOI":"10.1109\/ICICS49469.2020.239524"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"e2323","DOI":"10.7717\/peerj-cs.2323","article-title":"An AutoEncoder enhanced light gradient boosting machine method for credit card fraud detection","volume":"10","author":"Ding","year":"2024","journal-title":"PeerJ Comput. Sci."},{"key":"ref_36","first-page":"1","article-title":"Self-organizing maps, theory and applications","volume":"39","author":"Cottrell","year":"2018","journal-title":"Rev. Investig. Oper."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1007\/s41745-019-0102-z","article-title":"An overview of restricted Boltzmann machines","volume":"99","author":"Upadhya","year":"2019","journal-title":"J. Indian Inst. Sci."},{"key":"ref_38","unstructured":"Clearly-Payments (2025, March 10). How Merchants Can Reduce Fraud in Credit Card Processing. Available online: https:\/\/www.clearlypayments.com\/blog\/the-steps-to-reduce-fraud-in-credit-card-processing\/#:~:text=In%20the%20United%20States%2C%20credit%20card%20fraud,million)%20due%20to%20card%20fraud%20in%202020."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"67","DOI":"10.32996\/jefas.2024.6.1.7","article-title":"A review on financial fraud detection using ai and machine learning","volume":"6","author":"Kamuangu","year":"2024","journal-title":"J. Econ. Financ. Account. Stud."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"5673","DOI":"10.1002\/sim.9147","article-title":"Bayes estimate of primary threshold in clusterwise functional magnetic resonance imaging inferences","volume":"40","author":"Ge","year":"2021","journal-title":"Stat. Med."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"2778","DOI":"10.1093\/bioinformatics\/btaa042","article-title":"PARC: Ultrafast and accurate clustering of phenotypic data of millions of single cells","volume":"36","author":"Stassen","year":"2020","journal-title":"Bioinformatics"}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/9\/217\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:35:37Z","timestamp":1760034937000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/9\/217"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,25]]},"references-count":41,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["bdcc9090217"],"URL":"https:\/\/doi.org\/10.3390\/bdcc9090217","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,25]]}}}