Comparative evaluation of fraud detection algorithms in credit card transactions and online banking| International Journal of Innovative Science and Research Technology

Comparative Evaluation of Fraud Detection Algorithms in Credit Card Transactions and Online Banking

Authors : Moinul Islam

Volume/Issue : Volume 10 - 2025, Issue 12 - December

Google Scholar : https://tinyurl.com/aszd4z3n

Scribd : https://tinyurl.com/2mdadwbs

DOI : https://doi.org/10.38124/ijisrt/25dec632

PlumX Metrics

Semantic Scholar

ResearchGate

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : Credit card and online banking fraud have become a threat to financial security in the digital economy today and therefore require smart and automated detectors. The current study presents an AI-driven model of Credit Card Transaction Fraud Detection based on publicly available data on Credit Card Fraud Detection. The systematic workflow is the methodology, which is viewed as data preprocessing, feature selection, min-max scaling, and class balancing with the help of SMOTE. Machine learning and deep learning models included Extra Trees, ANN, and CatBoost that differentiated fraud and legitimate transactions. The measures of performance used in the evaluation were the accuracy, precision, recall, and the F1-score. The Extra Trees model which had an outstanding accuracy of 99.97 was above Cat Boost (99.74) and ANN (98.12) in the experiment. Moreover, among various Explainable AI methods, LIME and SHAP were utilized to enhance the interpretability of the model and identify the most significant factors that influence the fraud prediction. The proposed system as an appropriate solution to the real-life financial conditions enhances and increases the validity of fraud detection.

Keywords : Credit Card, Fraud Detection, Transaction, Machine Learning, Deep Learning, Banking.

References :

Y. Jain, N. Tiwari, S. Dubey, and S. Jain, “A Comparative Analysis of Various Credit Card Fraud Detection Techniques,” Int. J. Recent Technol. Eng., vol. 7, no. 5S2, 2019.
S. K. Tiwari, “Quality Assurance Strategies in Developing High-Performance Financial Technology Solutions,” Int. J. data Sci. Mach. Learn., vol. 05, no. 01, pp. 323–335, Jun. 2025, doi: 10.55640/ijdsml-05-01-26.
G. Mantha, “Transforming the Insurance Industry with Salesforce: Enhancing Customer Engagement and Operational Efficiency,” North Am. J. Eng. Res., vol. 5, no. 3, 2024.
S. J. Wawge, “A Survey on the Identification of Credit Card Fraud Using Machine Learning with Precision, Performance, and Challenges,” Int. J. Innov. Sci. Res. Technol., vol. 10, no. 4, May 2025, doi: 10.38124/ijisrt/25apr1813.
S. B. Shah, “Evaluating the Effectiveness of Machine Learning in Forecasting Financial Market Trends: A Fintech Perspective,” in 2025 3rd International Conference on Integrated Circuits and Communication Systems (ICICACS), 2025, pp. 1–6. doi: 10.1109/ICICACS65178.2025.10968297.
B. R. Ande, “Federated Learning and Explainable AI for Decentralised Fraud Detection in Financial Systems,” J. Inf. Syst. Eng. Manag., vol. 10, no. 35s, pp. 48–56, 2025, doi: 10.52783/jisem.v10i35s.5921.
S. R. Kurakula, “Architectural Challenges in Modernizing Legacy Financial Systems with Microservices and AI,” World J. Adv. Eng. Technol. Sci., vol. 15, no. 02, pp. 1328–1337, 2025.
B. Dharma and D. Latha, “Fraud Detection in Credit Card Transactional Data Using Hybrid Machine Learning Algorithm,” in 2025 6th International Conference on Mobile Computing and Sustainable Informatics (ICMCSI), 2025, pp. 213–218. doi: 10.1109/ICMCSI64620.2025.10883549.
J. Mishra, B. B. Biswal, and N. Padhy, “Machine Learning for Fraud Detection in Banking Cybersecurity Performance Evaluation of Classifiers and Their Real-Time Scalability,” in 2025 International Conference on Emerging Systems and Intelligent Computing (ESIC), IEEE, Feb. 2025, pp. 431–436. doi: 10.1109/ESIC64052.2025.10962752.
K. B. Thakkar and H. P. Kapadia, “The Roadmap to Digital Transformation in Banking: Advancing Credit Card Fraud Detection with Hybrid Deep Learning Model,” in 2025 2nd International Conference on Trends in Engineering Systems and Technologies (ICTEST), 2025, pp. 1–6. doi: 10.1109/ICTEST64710.2025.11042822.
V. S. Kiran, D. S. Rao, N. Sudeepthi, A. S. Sangars, V. R. Reddy, and N. Yalavarthi, “Detecting Credit Card Fraud Using Machine Learning Models,” in 2024 2nd International Conference on Recent Trends in Microelectronics, Automation, Computing and Communications Systems (ICMACC), 2024, pp. 823–828. doi: 10.1109/ICMACC62921.2024.10893907.
H. Kali, “Optimizing Credit Card Fraud Transactions identification and classification in banking industry Using Machine Learning Algorithms,” Int. J. Recent Technol. Sci. Manag., vol. 9, no. 11, pp. 85–96, 2024.
D. Singh, “Protecting Contactless Credit Card Payments from Fraud through Ambient Authentication and Machine Learning,” in ACCESS 2023 - 2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems, 2023. doi: 10.1109/ACCESS57397.2023.10200022.
V. Verma, “Deep Learning-Based Fraud Detection in Financial Transactions : A Case Study Using Real-Time Data Streams,” vol. 3, no. 4, pp. 149–157, 2023, doi: 10.56472/25832646/JETA-V3I8P117.
A. Gupta, K. Singh, N. Sharma, and M. Rakhra, “Machine Learning for Detecting Credit Card Fraud,” in 2022 IEEE North Karnataka Subsection Flagship International Conference, NKCon 2022, 2022. doi: 10.1109/NKCon56289.2022.10126861.
H. M. Shakeel, S. Iram, R. Hill, H. M. Athar Farid, A. Sheikh-Akbari, and F. Saleem, “A Machine Learning-Based Intelligent Framework for Predicting Energy Efficiency in Next-Generation Residential Buildings,” Buildings, vol. 15, no. 8, p. 1275, Apr. 2025, doi: 10.3390/buildings15081275.
A. Raza, K. Munir, M. Almutairi, F. Younas, and M. M. S. Fareed, “Predicting Employee Attrition Using Machine Learning Approaches,” Appl. Sci., vol. 12, no. 13, Jun. 2022, doi: 10.3390/app12136424.
A. M. Alsugair, K. S. Al-Gahtani, N. M. Alsanabani, A. A. Alabduljabbar, and A. S. Almohsen, “Artificial Neural Network Model to Predict Final Construction Contract Duration,” Appl. Sci., vol. 13, no. 14, p. 8078, Jul. 2023, doi: 10.3390/app13148078.
T. K. Shah, “Leadership in digital transformation: Enhancing customer value through AI-driven innovation in financial services marketing,” Int. J. Sci. Res. Arch., vol. 15, no. 03, pp. 618–627, 2025.
N. Malali, “Exploring Artificial Intelligence Models for Early Warning Systems with Systemic Risk Analysis in Finance,” in 2025 International Conference on Advanced Computing Technologies (ICoACT), IEEE, Mar. 2025, pp. 1–6. doi: 10.1109/ICoACT63339.2025.11005357.
Y. Wu, L. Wang, H. Li, and J. Liu, “A Deep Learning Method of Credit Card Fraud Detection Based on Continuous-Coupled Neural Networks,” Mathematics, vol. 13, no. 5, pp. 1–18, 2025, doi: 10.3390/math13050819.
A. R. Khalid, N. Owoh, O. Uthmani, M. Ashawa, J. Osamor, and J. Adejoh, “Enhancing Credit Card Fraud Detection: An Ensemble Machine Learning Approach,” Big Data Cogn. Comput., vol. 8, no. 1, pp. 1–6, Jan. 2024, doi: 10.3390/bdcc8010006.
M. A. Alrasheedi, “Enhancing Fraud Detection in Credit Card Transactions: A Comparative Study of Machine Learning Models,” Comput. Econ., Aug. 2025, doi: 10.1007/s10614-025-11071-3.
S. Saraf and A. Phakatkar, “Detection of Credit Card Fraud using a Hybrid Ensemble Model,” Int. J. Adv. Comput. Sci. Appl., vol. 3, no. 9, 2022, doi: 10.14569/IJACSA.2022.0130953

Credit card and online banking fraud have become a threat to financial security in the digital economy today and therefore require smart and automated detectors. The current study presents an AI-driven model of Credit Card Transaction Fraud Detection based on publicly available data on Credit Card Fraud Detection. The systematic workflow is the methodology, which is viewed as data preprocessing, feature selection, min-max scaling, and class balancing with the help of SMOTE. Machine learning and deep learning models included Extra Trees, ANN, and CatBoost that differentiated fraud and legitimate transactions. The measures of performance used in the evaluation were the accuracy, precision, recall, and the F1-score. The Extra Trees model which had an outstanding accuracy of 99.97 was above Cat Boost (99.74) and ANN (98.12) in the experiment. Moreover, among various Explainable AI methods, LIME and SHAP were utilized to enhance the interpretability of the model and identify the most significant factors that influence the fraud prediction. The proposed system as an appropriate solution to the real-life financial conditions enhances and increases the validity of fraud detection.

Keywords : Credit Card, Fraud Detection, Transaction, Machine Learning, Deep Learning, Banking.