Hybrid Machine Learning Models for Fraud Detection

Aadil Khan, Pramod Singh and Akhilesh A. Waoo

International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2026, vol. 12, issue 3, 168-174

Abstract: The rapid growth of digital payment systems, particularly in emerging economies such as India, has led to a substantial increase in online financial fraud. With billions of digital transactions processed monthly and transaction values exceeding trillions, the risk of cyber fraud has increased substantially. Traditional rule-based fraud detection systems, which rely on fixed rules and thresholds, are increasingly ineffective in addressing dynamic and sophisticated fraud patterns. This review paper provides a comprehensive analysis of machine learning and hybrid approaches for fraud detection in online transactions. It examines conventional techniques alongside widely used machine learning models such as Logistic Regression and Random Forest, as well as advanced deep learning methods, including Long Short-Term Memory. (LSTM). Particular focus is given to hybrid models that combine LSTM, Isolation Forest, and XGBoost to enhance detection performance. The study highlights that hybrid approaches can achieve accuracy levels above 95% while significantly reducing false positives by capturing temporal behavior, detecting anomalies, and improving classification efficiency. Key challenges identified include data imbalance, lack of real-time processing capabilities, and limited model interpretability. Furthermore, the paper discusses emerging research directions such as Explainable Artificial Intelligence (XAI), real-time fraud detection frameworks, and region-specific modeling tailored to digital payment ecosystems. These advancements are essential for developing scalable, adaptive, and reliable fraud detection systems in modern financial environments.

Keywords: Digital Payments; Fraud Detection; Hybrid Models; Isolation Forest; LSTM; Machine Learning; Risk Assessment; XGBoost (search for similar items in EconPapers)
Date: 2026
Note: Article URL: https://ijsrcseit.com/home/article/view/CSEIT2612321
References: Add references at CitEc
Citations:

Downloads: (external link)
https://ijsrcseit.com/home/article/view/CSEIT2612321 Article URL (text/html)
https://ijsrcseit.com/home/article/download/CSEIT2612321/CSEIT2612321 Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:jbh:ijsrcs:v12:y2026:i3:id:2003

DOI: 10.32628/CSEIT2612321

Access Statistics for this article

More articles in International Journal of Scientific Research in Computer Science, Engineering and Information Technology from International Journal of Scientific Research in Computer Science, Engineering and Information Technology
Bibliographic data for series maintained by Pankaj Sharma (USA) ().