International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Intelligent Fraud Detection and Prevention in Digital Banking |
|---|---|
| ABSTRACT | Digital payment systems have become indispensable for retail commerce, banking, and mobile-first financial services, but the same speed and convenience have also expanded the attack surface for fraud. A single rule-only mechanism is often too rigid to adapt to evolving attacker behavior, while a single machine learning classifier may struggle when the data are highly imbalanced, noisy, and temporally unstable. This paper presents a hybrid fraud detection framework that integrates supervised learning, anomaly detection, deterministic business rules, and a weighted fusion layer into a single operational pipeline. The project combines Gradient Boosting, Random Forest, a neural network validator, and Isolation Forest, while a final meta-decision layer consolidates the risk signals into a binary fraud judgment. The runtime service further includes merchant blacklisting, rapid transaction monitoring, location jump detection, and midnight high-value heuristics for immediate blocking. In addition to explaining the models, the paper details the preprocessing flow, feature engineering, model serialization, Flask-based prediction service, and transaction history logging. Architecture diagrams, workflow figures, rule charts, and design tables are included to show how layered fraud defense can be engineered for clarity, speed, and maintainability. |
| AUTHOR | P. RAJESH KUMAR, A. SURAJ KUMAR, V. RAKESH, G. KARTHIK, NITESH DANIEL, A. SAI VIVEK, V.LATHA, N. AKHIL Assistant Professor, Department of CSE (Data Science), NSRIT, Visakhapatnam, India Student, Department of CSE (Data Science), NSRIT, Visakhapatnam, India |
| VOLUME | 182 |
| DOI | DOI: 10.15680/IJIRCCE. 2026.1403071 |
| pdf/71_Intelligent Fraud Detection and Prevention in Digital Banking.pdf | |
| KEYWORDS | |
| References | 1. N. Baisholan, J. E. Dietz, S. Gnatyuk, M. Turdalyuly, E. T. Matson, and K. Baisholanova, "A Systematic Review of Machine Learning in Credit Card Fraud Detection Under Original Class Imbalance," Computers, vol. 14, no. 10, 437, 2025. 2. M. Tayebi and S. El Kafhali, "Generative Modeling for Imbalanced Credit Card Fraud Transaction Detection," Journal of Cybersecurity and Privacy, vol. 5, no. 1, 9, 2025. 3. H. Nguyen and B. Le, "Real-Time Transaction Fraud Detection via Heterogeneous Temporal Graph Neural Network," SCITEPRESS, 2025. 4. J. K. Afriyie et al., "A Supervised Machine Learning Algorithm for Detecting and Predicting Fraud in Credit Card Transactions," Decision Analytics Journal, vol. 6, 100163, 2023. 5. Fraud Detection Handbook, "Credit Card Fraud Detection System," Chapter 2 Background, reproducible-machine-learning-for-credit-card-fraud-detection, 2025. 6. L. Breiman, "Random Forests," Machine Learning, vol. 45, pp. 5-32, 2001. 7. I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, 2016. 8. T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning, 2nd ed., Springer, 2009. 9. Scikit-learn Developers, "scikit-learn: Machine Learning in Python," official documentation. 10. Imbalanced-learn Developers, "Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets," official documentation. |
