Citation:

Varun Verma, 2023. "Deep Learning-Based Fraud Detection in Financial Transactions: A Case Study Using Real-Time Data Streams", ESP Journal of Engineering & Technology Advancements  3(4): 149-157.

Abstract:

Credit card fraud continues to be a major challenge for financial institutions, especially with the increasing volume and speed of online transactions. Traditional rule-based fraud detection systems are often unable to adapt to the evolving patterns of fraudulent behavior. In this paper, we present a deep learning-based framework for credit card fraud detection using artificial neural networks (ANN) and advanced convolution neural network (CNN) architectures such as VGG16 and VGG19. The system processes credit card transactions and applies deep learning models to classify them as fraudulent or legitimate. ANN is used as a baseline model due to its simplicity and speed, while VGG16 and VGG19 are fine-tuned to learn complex features and detect subtle anomalies in transaction patterns. To address the inherent class imbalance in fraud datasets, Synthetic Minority Over-Sampling Technique (SMOTE) is applied to generate synthetic fraudulent samples, along with random under-sampling of the majority class. Principal Component Analysis (PCA) is employed to reduce data dimensionality, improving model efficiency and reducing computation time. Experimental results on a benchmark credit card dataset show that VGG16 and VGG19 outperform the ANN model in terms of accuracy, precision, and recall, with VGG19 achieving the highest performance. This study demonstrates the potential of deep CNN architectures combined with stream processing to build scalable and effective solutions for credit card fraud detection in dynamic financial environments.

References:

[1] Iwasokun GB, Omomule TG, Akinyede RO. Encryption and tokenization-based system for credit card information security. Int J Cyber Sec Digital Forensics. 2018;7(3):283–93.

[2] Burkov A. The hundred-page machine learning book. 2019;1:3–5.

[3] Maniraj SP, Saini A, Ahmed S, Sarkar D. Credit card fraud detection using machine learning and data science. Int J Eng Res 2019; 8(09). 4. Dornadula VN, Geetha S. Credit card fraud detection using machine learning algorithms. Proc Comput Sci. 2019;165:631–41

[4] Thennakoon, Anuruddha, et al. Real-time credit card fraud detection using machine learning. In: 2019 9th international conference on cloud computing, data science & engineering (Confuence). IEEE; 2019.

[5] Visa credit cards in circulation 2020|Statista. In: Statista. 2021. https://www.statista.com/statistics/618115/number-of-visa-creditcards-worldwide-by-region/. Mastercard: credit cards in circulation 2021|Statista. In: Statista. 2021 https://www.statista.com/statistics/618137/number-of-maste rcard-credit-cards-worldwide-by-region/. Accessed 24 Nov 2021.

[6] P. Save, P. Tiwarekar, K. N., and N. Mahyavanshi, ―A Novel Idea for Credit Card Fraud Detection using Decision Tree,‖ Int. J. Comput. Appl., vol. 161, no. 13, pp. 6–9, 2017, doi: 10.5120/ijca2017913413.

[7] J. Vimala Devi and K. S. Kavitha, ―Fraud Detection in Credit Card Transactions by using Classification Algorithms,‖ Int. Conf. Curr. Trends Comput. Electr. Electron. Commun. CTCEEC 2017, pp. 125–131, 2018, doi: 10.1109/CTCEEC.2017.8455091.

[8] R. R. Popat and J. Chaudhary, ―A Survey on Credit CardFraud Detection Using Machine Learning,‖ Proc. 2ndInt.Conf. Trends Electron. Informatics, ICOEI 2018, no. Icoei, pp. 1120–1125, 2018, oi:10.1109/ICOEI.2018.8553963.

[9] S. Xuan, G. Liu, Z. Li, L. Zheng, S. Wang, and C. Jiang,―Random forest for credit card fraud detection,‖ ICNSC2018 - 15th IEEE Int. Conf. Networking, Sens. Control, pp.1–6, 2018, doi: 10.1109/ICNSC.2018.8361343.

[10] S. Mittal and S. Tyagi, ―Performance evaluation of machine learning algorithms for credit card fraud detection,‖ Proc. 9th Int. Conf. Cloud Comput. Data Sci.Eng. Conflu. 2019, pp. 320–324, 2019, doi:10.1109/CONFLUENCE.2019.8776925.

[11] X. Yu, X. Li, Y. Dong, and R. Zheng, ―A Deep Neural Network Algorithm for Detecting Credit Card Fraud,‖ Proc. - 2020 Int. Conf. Big Data, Artif. Intell. Internet Things Eng. ICBAIE 2020, pp. 181–183, 2020, doi:10.1109/ICBAIE49996.2020.00045.

[12] S. Bagga, A. Goyal, N. Gupta, andA. Goyal, ―Credit CardFraud Detection using Pipeling and Ensemble Learning,‖ Procedia Comput. Sci., vol. 173, pp. 104–112, 2020, doi: 10.1016/j.procs.2020.06.014.

[13] R. San Miguel Carrasco and M.-A. Sicilia-Urban,―Evaluationof Deep Neural Networks for Reduction of Credit Card Fraud Alerts,‖ IEEE Access, vol. 8, pp. 186421–186432, 2020, doi: 10.1109/access.2020.3026222.

Keywords:

Credit Card Fraud Detection, Machine Learning, Lightgbm, Gradient Boosting, Real-Time Detection, Financial Fraud, Feature Engineering, Model Evaluation.