LSTM Model for Credit Card Fraud Detection

Buchi Nzegwu, Nurudeen M. Ibrahim

Abstract


The financial system plays a crucial role in managing and transferring money and assets, with credit cards serving as a primary means of transaction. While credit cards offer convenience, they also present security challenges, as fraudsters continuously attempt to exploit vulnerabilities. Detecting fraudulent transactions is essential to mitigating financial losses. This study develops a robust fraud detection model using Long Short-Term Memory (LSTM) networks. While LSTMs have been widely used in credit card fraud detection, our approach introduces key architectural modifications that enhance stability, regularization, and feature transformation. These modifications improve model generalization and performance in detecting fraudulent transactions. Given the highly imbalanced nature of the dataset where fraud accounts for only 0.6% of training data and 0.3% of test data Synthetic Minority Over-Sampling Technique (SMOTE) is employed to generate synthetic samples for the minority class in the training set. The model’s performance is evaluated using key metrics such as accuracy, precision, recall, F1-score, and the AUC-ROC curve.


Full Text:

PDF

References


Cherif, Asma, Badhib, Arwa, Ammar, Heyfa, Alshehri, Suhair, Kalkatawi, Manal, & Imine, Abdessamad. (2023). Credit card fraud detection in the era of disruptive technologies: A systematic review. Journal of King Saud University-Computer and Information Sciences, 35(1), 145-174.

Hasib, Khan Md, Iqbal, Md Sadiq, Shah, Faisal Muhammad, Mahmud, Jubayer Al, Popel, Mahmudul Hasan, Showrov, Md Imran Hossain, . . . Rahman, Obaidur. (2020). A survey of methods for managing the classification and solution of data imbalance problem. arXiv preprint arXiv:2012.11870.

Karkaba, IMANE, Adnani, EM, & Erritali, M. (2023). Deep Learning Detecting Fraud in Credit Card Transactions. Journal of Theoretical and Applied Information Technology, 101(9).

Liu, Kai, & Zhang, Jie. (2021). A dual-layer attention-based LSTM network for fed-batch fermentation process modelling Computer aided chemical engineering (Vol. 50, pp. 541-547): Elsevier.

Mallidi, Manoj Kumar Reddy, & Zagabathuni, Yeshwanth. (2021). Analysis of Credit Card Fraud detection using Machine Learning models on balanced and imbalanced datasets. International Journal of Emerging Trends in Engineering Research, 9(7).

Mienye, Ibomoiye Domor, & Jere, Nobert. (2024). Deep learning for credit card fraud detection: A review of algorithms, challenges, and solutions. IEEE Access.

Staudemeyer, Ralf C, & Morris, Eric Rothstein. (2019). Understanding LSTM--a tutorial into long short-term memory recurrent neural networks. arXiv preprint arXiv:1909.09586.

Thabtah, Fadi, Hammoud, Suhel, Kamalov, Firuz, & Gonsalves, Amanda. (2020). Data imbalance in classification: Experimental evaluation. Information Sciences, 513, 429-441.

Swipesum, “The history of the credit card,” https://www.swipesum.com/insights/history-of-the-credit-card. Statista, “Global card fraud losses worldwide from 2014 to2023,”https://www.statista.com/statistics/1394119/global-card-fraud-losses/.


Refbacks

  • There are currently no refbacks.