Mitigating Online Banking Fraud Using Machine Learning and Anomaly Detection

Online banking fraud has become increasingly prevalent with the widespread adoption of digital financial services, necessitating advanced security solutions capable of detecting both known and emerging threats. This paper presents a robust machine learning framework that integrates anomaly detection...

Full description

Saved in:
Bibliographic Details
Main Authors: Sheunesu Makura, Caden Dobson, Seani Rananga
Format: Article
Language:English
Published: Informatics Department, Faculty of Computer Science Bina Darma University 2025-06-01
Series:Journal of Information Systems and Informatics
Subjects:
Online Access:https://journal-isi.org/index.php/isi/article/view/1076
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849240651345952768
author Sheunesu Makura
Caden Dobson
Seani Rananga
author_facet Sheunesu Makura
Caden Dobson
Seani Rananga
author_sort Sheunesu Makura
collection DOAJ
description Online banking fraud has become increasingly prevalent with the widespread adoption of digital financial services, necessitating advanced security solutions capable of detecting both known and emerging threats. This paper presents a robust machine learning framework that integrates anomaly detection with network packet analysis to mitigate fraudulent activities, focusing particularly on Distributed Denial of Service (DDoS) attacks. The key contribution is an ensemble model combining Isolation Forest and K-means clustering, which achieves 98% accuracy and 98% F1-score in anomaly detection while reducing false positives to 2% which is a critical improvement for operational deployment in banking systems. The framework’s semi-supervised architecture enables zero-day fraud detection without reliance on labeled attack data, addressing a fundamental limitation of signature-based systems. By leveraging feature optimization (PCA/t-SNE) and real-time processing capabilities, this solution offers financial institutions a practical, adaptive defense mechanism against evolving cyber threats. The results demonstrate significant potential for integration into existing banking security infrastructures to enhance fraud prevention with minimal disruption.
format Article
id doaj-art-94ec9c1b09fa4e6fa3a195388a6dc86b
institution Kabale University
issn 2656-5935
2656-4882
language English
publishDate 2025-06-01
publisher Informatics Department, Faculty of Computer Science Bina Darma University
record_format Article
series Journal of Information Systems and Informatics
spelling doaj-art-94ec9c1b09fa4e6fa3a195388a6dc86b2025-08-20T04:00:28ZengInformatics Department, Faculty of Computer Science Bina Darma UniversityJournal of Information Systems and Informatics2656-59352656-48822025-06-01721153118310.51519/journalisi.v7i2.10761076Mitigating Online Banking Fraud Using Machine Learning and Anomaly DetectionSheunesu Makura0Caden Dobson1Seani Rananga2University of PretoriaUniversity of PretoriaUniversity of PretoriaOnline banking fraud has become increasingly prevalent with the widespread adoption of digital financial services, necessitating advanced security solutions capable of detecting both known and emerging threats. This paper presents a robust machine learning framework that integrates anomaly detection with network packet analysis to mitigate fraudulent activities, focusing particularly on Distributed Denial of Service (DDoS) attacks. The key contribution is an ensemble model combining Isolation Forest and K-means clustering, which achieves 98% accuracy and 98% F1-score in anomaly detection while reducing false positives to 2% which is a critical improvement for operational deployment in banking systems. The framework’s semi-supervised architecture enables zero-day fraud detection without reliance on labeled attack data, addressing a fundamental limitation of signature-based systems. By leveraging feature optimization (PCA/t-SNE) and real-time processing capabilities, this solution offers financial institutions a practical, adaptive defense mechanism against evolving cyber threats. The results demonstrate significant potential for integration into existing banking security infrastructures to enhance fraud prevention with minimal disruption.https://journal-isi.org/index.php/isi/article/view/1076machine learningfraud mitigationonline bankinganomaly detectionnetwork packetsfraud detection
spellingShingle Sheunesu Makura
Caden Dobson
Seani Rananga
Mitigating Online Banking Fraud Using Machine Learning and Anomaly Detection
Journal of Information Systems and Informatics
machine learning
fraud mitigation
online banking
anomaly detection
network packets
fraud detection
title Mitigating Online Banking Fraud Using Machine Learning and Anomaly Detection
title_full Mitigating Online Banking Fraud Using Machine Learning and Anomaly Detection
title_fullStr Mitigating Online Banking Fraud Using Machine Learning and Anomaly Detection
title_full_unstemmed Mitigating Online Banking Fraud Using Machine Learning and Anomaly Detection
title_short Mitigating Online Banking Fraud Using Machine Learning and Anomaly Detection
title_sort mitigating online banking fraud using machine learning and anomaly detection
topic machine learning
fraud mitigation
online banking
anomaly detection
network packets
fraud detection
url https://journal-isi.org/index.php/isi/article/view/1076
work_keys_str_mv AT sheunesumakura mitigatingonlinebankingfraudusingmachinelearningandanomalydetection
AT cadendobson mitigatingonlinebankingfraudusingmachinelearningandanomalydetection
AT seanirananga mitigatingonlinebankingfraudusingmachinelearningandanomalydetection