{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T05:55:23Z","timestamp":1790920523144,"version":"4.1.0"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T00:00:00Z","timestamp":1790899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Financial transaction fraud detection is a challenging binary classification problem characterized by severe class imbalance, rare fraudulent cases, and asymmetric misclassification costs. In real-world banking systems, failing to detect fraudulent transactions can lead to substantial financial losses, whereas false alarms mainly increase operational review costs. Therefore, fraud detection models should not be optimized only for overall accuracy, as accuracy-oriented classifiers may favor the majority non-fraud class and fail to identify minority fraud cases effectively. To address this issue, this study proposes a cost-sensitive ML framework for financial transaction fraud detection under class imbalance and asymmetric financial risk.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this study, a cost-sensitive RF framework with adaptive probability threshold optimization is proposed for binary fraud classification. Misclassification costs are incorporated during model training through class-weighted learning, allowing the classifier to assign greater importance to minority fraud cases. In addition, instead of using the default probability threshold of 0.5, the decision threshold is optimized using validation data to minimize the expected misclassification cost and improve minority-class detection. The proposed framework was evaluated on two publicly available financial fraud datasets with different transaction characteristics: the Credit Card Fraud Detection dataset and the Financial Fraud Prediction dataset. Its performance was compared with conventional ML baselines using fraud-oriented evaluation metrics, including precision, recall, F1-score, false-negative rate, false-positive rate, and expected misclassification cost.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed framework achieved strong and consistent performance across both datasets. On the Credit Card Fraud Detection dataset, it achieved a precision of 94.4%, recall of 85.7%, and F1-score of 89.8%. On the Financial Fraud Prediction dataset, it achieved a precision of 93.1%, a recall of 83.8%, and an F1-score of 88.2%. Compared with conventional fixed-threshold ML models, the adaptive threshold strategy reduced false-negative predictions while maintaining high precision. These results indicate that the proposed cost-sensitive framework provides a more balanced decision strategy for fraud detection under highly imbalanced transaction distributions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The findings demonstrate that combining class-weighted learning with adaptive threshold optimization can improve fraud detection performance under asymmetric misclassification costs. The proposed framework offers a practical and interpretable decision-support approach for banking fraud detection systems, particularly in settings where reducing undetected fraudulent transactions is more important than maximizing overall accuracy alone.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1938836","type":"journal-article","created":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T05:35:20Z","timestamp":1790919320000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Cost-sensitive random forest with adaptive threshold optimization for imbalanced financial fraud detection"],"prefix":"10.3389","volume":"9","author":[{"given":"Jafar","family":"Ali","sequence":"first","affiliation":[{"name":"School of Business, Yeungnam University","place":["Gyeongsan, Gyeongbuk, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rahman","family":"Shafique","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, Yeungnam University","place":["Gyeongsan, Gyeongbuk, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Gavilanes","sequence":"additional","affiliation":[{"name":"Universidad Europea del Atl\u00e1ntico","place":["Santander, Spain"]},{"name":"Universidad Internacional Iberoamericana","place":["Campeche, Mexico"]},{"name":"Universidade Internacional do Cuanza","place":["Cuito, Bi\u00e9, Angola"]},{"name":"Fundaci\u00f3n Universitaria Internacional de Colombia","place":["Bogot\u00e1, Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manuel Masias","family":"Vergara","sequence":"additional","affiliation":[{"name":"Universidad Europea del Atl\u00e1ntico","place":["Santander, Spain"]},{"name":"Universidad Internacional Iberoamericana","place":["Arecibo, PR, United States"]},{"name":"Universidad de La Romana","place":["La Romana, Dominican Republic"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isabel","family":"de la Torre Diez","sequence":"additional","affiliation":[{"name":"Department of Signal Theory and Communications and Telematic Engineering, University of Valladolid","place":["Valladolid, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dae Wan","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Business, Yeungnam University","place":["Gyeongsan, Gyeongbuk, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,2]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"100163","DOI":"10.1016\/j.dajour.2023.100163","article-title":"A supervised machine learning algori thm for detecting and predicting fraud in credit card transactions","volume":"6","author":"Afriyie","year":"2023","journal-title":"Decis. Anal. J."},{"key":"B2","doi-asserted-by":"publisher","first-page":"100675","DOI":"10.1016\/j.mlwa.2025.100675","article-title":"A credit card fraud detection approach based on ensemble machine learning classifier with hybrid data sampling","volume":"20","author":"Ahmed","year":"2025","journal-title":"Mach. Learn. Appl"},{"key":"B3","doi-asserted-by":"publisher","first-page":"100675","DOI":"10.1016\/j.mlwa.2025.100675","article-title":"A credit card fraud detection approach based on ensemble machine learning classifier with hybrid data sampling","volume":"20","author":"Ahmed","year":"2025","journal-title":"Mach. Learn. Appl"},{"key":"B4","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.gltp.2021.01.006","article-title":"Credit card fraud detection using artificial neural network","volume":"2","author":"Asha","year":"2021","journal-title":"Glob. Transit. Proc"},{"key":"B5","doi-asserted-by":"publisher","first-page":"6609","DOI":"10.1016\/j.eswa.2015.04.042","article-title":"Example dependent cost sensitive decision trees","volume":"42","author":"Bahnsen","year":"2015","journal-title":"Expert Syst. Appl"},{"key":"B6","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1177\/1555458914549669","article-title":"Fraud and corruption control at education system level: a case study of the victorian department of education and early childhood development in Australia","volume":"17","author":"Bandaranayake","year":"2014","journal-title":"J. Cases Educ. Leadersh"},{"key":"B7","volume-title":"Feature Selection for a Better Imbalanced Data Classification: A Financial Fraud Detection Case","author":"Breskuvien\u0117","year":"2025"},{"key":"B8","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1214\/20-BA1254","article-title":"Bayesian quickest detection of credit card fraud","volume":"17","author":"Buonaguidi","year":"2022","journal-title":"Bayesian Analys"},{"key":"B9","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.inffus.2017.09.005","article-title":"Scarff: a scalable framework for streaming credit card fraud detection with spark","volume":"41","author":"Carcillo","year":"2018","journal-title":"Inf. Fusion"},{"key":"B10","doi-asserted-by":"publisher","first-page":"7788","DOI":"10.3390\/s23187788","article-title":"Credit card fraud detection: an improved strategy for high recall using KNN, LDA, and linear regression","volume":"23","author":"Chung","year":"2023","journal-title":"Sensors"},{"key":"B11","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1109\/SSCI.2015.33","article-title":"\u201cCalibrating probability with undersampling for unbalanced classification,\u201d","author":"Dal Pozzolo","year":"2015","journal-title":"2015 IEEE symposium series on computational intelligence"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2015.33","article-title":"\u201cCalibrating probability with undersampling for unbalanced classification,\u201d","author":"Dal Pozzolo","year":"2015","journal-title":"2015 IEEE symposium series on computational intelligence"},{"key":"B13","doi-asserted-by":"publisher","first-page":"158939","DOI":"10.1109\/ACCESS.2024.3487298","article-title":"Machine learning methods for credit card fraud detection: a survey","volume":"12","author":"Dastidar","year":"2024","journal-title":"IEEE Access"},{"key":"B14","doi-asserted-by":"publisher","first-page":"158939","DOI":"10.1109\/ACCESS.2024.3487298","article-title":"Machine learning methods for credit card fraud detection: a survey","volume":"12","author":"Dastidar","year":"2024","journal-title":"IEEE Access"},{"key":"B15","doi-asserted-by":"publisher","first-page":"16400","DOI":"10.1109\/ACCESS.2022.3148298","article-title":"A neural network ensemble with feature engineering for improved credit card fraud detection","volume":"10","author":"Esenogho","year":"2022","journal-title":"IEEE Access"},{"key":"B16","doi-asserted-by":"publisher","first-page":"185","DOI":"10.32604\/cmc.2019.06144","article-title":"Credit card fraud detection based on machine learning","volume":"61","author":"Fang","year":"2019","journal-title":"Comput. Mater. Contin"},{"key":"B17","doi-asserted-by":"publisher","first-page":"252","DOI":"10.32996\/jbms.2024.6.13.21","article-title":"Enhancing credit card fraud detection: a comprehensive study of machine learning algorithms and performance evaluation","volume":"6","author":"Farabi","year":"2024","journal-title":"J. Bus. Manag. Stud"},{"key":"B18","doi-asserted-by":"publisher","first-page":"111368","DOI":"10.1016\/j.asoc.2024.111368","article-title":"Imbalanced credit card fraud detection data: a solution based on hybrid neural network and clu stering based undersampling technique","volume":"154","author":"Huang","year":"2024","journal-title":"Appl. Soft Comput"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1950","DOI":"10.3390\/math13121950","article-title":"Enhanced credit card fraud detection using deep hybrid CLST model","volume":"13","author":"Jabeen","year":"2025","journal-title":"Mathematics"},{"key":"B20","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1016\/j.eswa.2018.01.037","article-title":"Sequence classification for credit card fraud detection","volume":"100","author":"Jurgovsky","year":"2018","journal-title":"Expert Syst. Appl"},{"key":"B21","first-page":"108088","article-title":"Imbalanced credit card fraud detection using cost-sensitive random forest","volume":"114","author":"Li","year":"2022","journal-title":"Appl. Soft Comput"},{"key":"B22","article-title":"\u201cPaysim: a financial mobile money simulator for fraud detection,\u201d","volume-title":"Proceedings of the 28th European modeling and simulation symposium (EMSS)","author":"Lopez-Rojas","year":"2016"},{"key":"B23","doi-asserted-by":"publisher","first-page":"93010","DOI":"10.1109\/ACCESS.2019.2927266","article-title":"An experimental study with imbalanced classification approaches for credit card fraud detection","volume":"7","author":"Makki","year":"2019","journal-title":"IEEE Access"},{"key":"B24","doi-asserted-by":"publisher","author":"Mula","year":"2025","DOI":"10.37745\/ejcsit.2013\/vol13n1086100"},{"key":"B25","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.inffus.2008.04.001","article-title":"Credit card fraud detection: a fusion approach using dempster-shafer theory and bayesian learning","volume":"10","author":"Panigrahi","year":"2009","journal-title":"Inf. Fusion"},{"key":"B26","doi-asserted-by":"publisher","first-page":"14277","DOI":"10.1109\/ACCESS.2018.2806420","article-title":"Credit card fraud detection using AdaBoost and majority voting","volume":"6","author":"Randhawa","year":"2018","journal-title":"IEEE Access"},{"key":"B27","doi-asserted-by":"publisher","first-page":"681","DOI":"10.3390\/cancers15030681","article-title":"Breast cancer prediction using fine needle aspiration features and upsampling with supervised machine learning","volume":"15","author":"Shafique","year":"2023","journal-title":"Cancers"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1681","DOI":"10.17485\/IJST\/v18i21.903","article-title":"Benchmarking machine learning techniques for credit card fraud detection","volume":"18","author":"Shah","year":"2025","journal-title":"Indian J. Sci. Technol"},{"key":"B29","doi-asserted-by":"publisher","first-page":"e0326975","DOI":"10.1371\/journal.pone.0326975","article-title":"Hybrid feature selection framework for enhanced credit card fraud detection using machine learning models","volume":"20","author":"Siam","year":"2025","journal-title":"PLoS ONE"},{"key":"B30","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1007\/s10618-008-0116-z","article-title":"Transaction aggregation as a strategy for credit card fraud detection","volume":"18","author":"Whitrow","year":"2009","journal-title":"Data Min. Knowl. Discov"},{"key":"B31","first-page":"1","article-title":"Analyzing the economic impact of credit card fraud: activation, limit upgrades, cashback scams, discount fraud, and overdraft risks","volume":"9","author":"Yoganandham","year":"2024","journal-title":"Degr\u00e9s"},{"key":"B32","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1016\/j.procs.2015.04.201","article-title":"Application of credit card fraud detection: based on bagging ensemble classifier","volume":"48","author":"Zareapoor","year":"2015","journal-title":"Proc. Comput. Sci"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1938836\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T05:35:21Z","timestamp":1790919321000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1938836\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,2]]},"references-count":32,"alternative-id":["10.3389\/frai.2026.1938836"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1938836","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,2]]},"article-number":"1938836"}}