{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T15:45:18Z","timestamp":1776440718847,"version":"3.51.2"},"reference-count":0,"publisher":"Advances in Artificial Intelligence and Machine Learning","issue":"02","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAIML"],"published-print":{"date-parts":[[2025]]},"abstract":"<jats:p>Cyberfraud is a major threat to the banking and financial institutions globally and South Africa is not an exemption. The deep learning (DL) technique for cyberfraud incidence classification and time series prediction using the South African financial institutions as a case study was demonstrated in this study. Secondary data from the South African Banking Risk Information Centre (SABRIC) was employed and the data was trained under the DL paradigms of Convolutional Neural Network (CNN) and the Long Short-Term Memory (LSTM) model. For both models, the adaptive moment estimation (ADAM) algorithm was employed for fraud incidence classification while the time series model was used for the future prediction of fraud incidences. On the overall, the LSTM model with an accuracy of 96.80% outperformed the CNN model with an overall accuracy of 96.17%. Moreover, the accuracy, precision, recall and F1-score of the LSTM classification model namely 72.14%, 87.43% and 77.31% respectively exceeded 70%. The results show that the DL model can be deployed for fraud classification and time series analysis of fraud incidences. The outcome of this study may promote cyber resilience and sustain the fight against the perpetration of cyber-related fraud in the South Africa. The use of the CNN and LSTM models for cyberfraud classification and time series prediction of cyberfraud incidences demonstrated in this study is unique. This study contributes conceptually, theoretically and empirical to knowledge on cyberfraud mitigation. It proposes an artificial intelligence based conceptual framework for reinforcing cybersecurity in the financial institution.<\/jats:p>","DOI":"10.54364\/aaiml.2025.52226","type":"journal-article","created":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T12:18:47Z","timestamp":1751372327000},"page":"4004-4033","source":"Crossref","is-referenced-by-count":1,"title":["Mitigating Cyberfraud in Financial Institutions: A Deep Learning Approach using the South African Banking Industry as a Case Study"],"prefix":"10.54364","volume":"05","author":[{"given":"Oluwatoyin Esther","family":"Akinbowale","sequence":"first","affiliation":[]},{"given":"Mulatu Fekadu","family":"Zerihun","sequence":"additional","affiliation":[]},{"given":"Polly","family":"Mashigo","sequence":"additional","affiliation":[]}],"member":"32807","published-online":{"date-parts":[[2025]]},"container-title":["Advances in Artificial Intelligence and Machine Learning"],"original-title":[],"link":[{"URL":"https:\/\/www.oajaiml.com\/uploads\/archivepdf\/877752226.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T12:18:49Z","timestamp":1751372329000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.oajaiml.com\/uploads\/archivepdf\/877752226.pdf"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":0,"journal-issue":{"issue":"02","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.54364\/aaiml.2025.52226","relation":{},"ISSN":["2582-9793"],"issn-type":[{"value":"2582-9793","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}