Intelligent Credit Card Fraud Detection System | IJCT Volume 13 – Issue 2 | IJCT-V13I2P66
International Journal of Computer Techniques
ISSN 2394-2231
Author
Gujjula Srisahajananda, Madala Rosaiaha Chowdary, Madamshetty Vamshi, Ms.R Santhana Lakshmi
Abstract
Credit card fraud has emerged as a key issue for the financial sector due to the increase in the number of cashless transactions. Traditional rule-based anti-fraud techniques are not found to perform well in the detection of complex credit card fraud patterns. [3]This paper introduces a machine learning approach for credit card fraud detection, inspired by earlier researchers in the field of data mining for credit card fraud detection. The proposed system follows a supervised learning approach to identify fraud transactions in a cashless environment. An appropriate preprocessing approach is adopted for handling class imbalance. The performance of these models is quantified through accuracy measures such as precision, recall, accuracy, and F1 score[6]; these are more appropriate for fraud detection problems compared to accuracy. The experiment results show that machine learning can improve fraud detection performance significantly compared to traditional approaches. This paper also emphasizes data-driven fraud detection approaches and their significant role in developing credit card fraud detection models that are trustworthy and scalable.
Keywords
Credit Card Fraud Detection, Machine Learning, Data Mining, Imbalanced
Dataset, Classification Algorithms, Financial Security
Conclusion
Thus, it can be concluded that the proposed system will provide an efficient solution for the detection of credit card fraud, which would not only reduce losses but also eliminate false alarms[14]. This article emphasizes the need for data-driven and dynamic approaches to machine learning for improving the security of financial transaction System From the experiment performed, it is evident that the Random Forest classifier is better than other machine learning models, especially in terms of accuracy and detection capabilities[17]. It is apparent that employing multiple evaluation mechanisms, like precision, recall, and F1 score, is a suitable strategy for evaluating model competencies, particularly when dealing with class imbalance problems. Indeed, ensemble models are more consistent while detecting sophisticated fraudulent patterns.
References
[1]Adversarial Drift Detection (IJCNN2014) https://ieeexplore.ieee.org/document/6889387
[2]Credit Card Fraud Detection Using Machine LearningTechniques(IJERT2020) https://www.ijert.org/credit-card-fraud- detectionusing-machine-learning-techniques
[3]Data Mining for Credit Card Fraud: A Comparative Study(Decision Support Systems) https://www.sciencedirect.com/science/article/pii
/S 0167923610002604
[4]SCARFF: A Scalable Framework for Streaming CreditCardFraudDetection https://www.sciencedirect.com/science/article/pii/S 156625351730628X
[5]XGBoost: A Scalable Tree Boosting System https://dl.acm.org/doi/10.1145/2939672.2939785
[6]UCI Machine Learning Repository – Credit Card Dataset https://archive.ics.uci.edu/
[7]Kaggle – European Credit Card Fraud Dataset https://www.kaggle.com/mlg-ulb/creditcardfraud
[8]SMOTE: Synthetic Minority Over-sampling Technique https://jair.org/index.php/jair/article/view/10302
[9]Chen & Guestrin (2016) – Gradient Boosting for Fraud Detection Proceedings of ACM SIGKDD Conference https://dl.acm.org/doi/10.1145/2939672.2939785
[10]Anomaly Detection for CreditCard Fraud https://www.sciencedirect.com/science/article/pii/S1877050 91831097
[11]Handling Imbalanced Datasets in Machine Learning – ACM Computing Surveys
https://dl.acm.org/doi/10.1145/3344996
[12] Random Forests – Leo Breiman (FoundationalPaper) https://www.stat.berkeley.edu/~breiman/rando mforest2001.pdf
[13]Logistic Regression in Credit Risk and Fraud Detection https://link.springer.com/chapter/10.1007/978-3- 030-16841-4_6
[14]A Survey of Credit Card Fraud Detection Methods – IEEE Access https://ieeexplore.ieee.org/document/8254255
[15]Isolation Forest Algorithm for Anomaly Detection https://ieeexplore.ieee.org/document/4781136
[16]Credit Card Fraud Detection: A Realistic Modeling and New Public Dataset – Dal Pozzolo et al. https://ieeexplore.ieee.org/document/7475706
[17]Machine Learning for Credit Card Fraud Detection – A Comparative Study https://www.researchgate.net/publication/328078 670
[18]IEEE Xplore – Credit Card Fraud Detection Research Collection https://ieeexplore.ieee.org/search/searchresult.jsp
?queryText=credit%20card%20fraud%20detecti on
How to Cite This Paper
Gujjula Srisahajananda, Madala Rosaiaha Chowdary, Madamshetty Vamshi, Ms.R Santhana Lakshmi (2026). Intelligent Credit Card Fraud Detection System. International Journal of Computer Techniques, 13(2). ISSN: 2394-2231.
