A Deep Learning-Based Framework for Detecting Synthetic Identity Fraud in Digital Credit Card Applications
DOI:
https://doi.org/10.63282/3050-922X.IJERET-V4I4P105Keywords:
Synthetic Identity Fraud, Deep Learning, Credit Card Applications, Neural Networks, Anomaly DetectionAbstract
Innovation in the digitalization era has exposed the financial institutions to the most challenges of verifying their customer identities because of the spike in Synthetic Identity Fraud (SIF). This kind of fraud refers to a mix of true and false elements of identity to invent a fictitious identity in order to duplicate the fictitious identity and use it to cheat credit systems. Such attacks are especially prone to the digital credit card application process, which is a convenient method. The current systems of identifying fraud through rule-based systems and classical machine learning techniques struggle to keep pace with the intelligence of these top-level fraudsters. Due to this, the paper is suggested to involve a deep learning framework that is customised to identify synthetic identity fraud in the digital credit card applications. The solution that we propose utilizes the family of neural networks, an ensemble that incorporates the Convolutional Neural Networks (CNNs) and the Recursive Neural Networks (RNNs) with Long Short-Term Memory (LSTM) to train feature extraction and learning of sequences, respectively. The framework is trained with an augmented dataset generated to represent the actual real-life credit application data, combined with embedded, generated fake patterns. The features of the data are preprocessed with sophisticated types of feature engineering, such as identity clustering, behavioral anomaly detection, and multi-source data fusion. The model architecture will implement attention mechanisms to draw attention to some abnormal characteristics of identity that can indicate a fraud situation, but also enable the system to specialise in key fraud indicators. Another autoencoder network is used to further detect through modeling the identity profiles that are legitimate to tag any anomalies, depending on the reconstruction loss. Various experiments prove that our framework can outperform baseline machine learning methods by 15 percent in F1-score and fewer false positives. In this paper, the author brings to the table an in-depth discussion on synthetic identity fraud attacks, how they are difficult to detect, and the possibility of deep learning models in curbing such attacks. It also presents novel labeled data to benchmark fraud detection systems that will be of use in future studies. Our findings are that the deep learning system with proper implementation offers a sound counter to synthetic identity fraud prevention, and paves the way to smart fraud apprehensive systems in financial services
References
[1] Bhattacharyya, S., Jha, S., Tharakunnel, K., & Westland, J. C. (2011). Data mining for credit card fraud: A comparative study. Decision support systems, 50(3), 602-613.
[2] Phua, C., Lee, V., Smith, K., & Gayler, R. (2010). A comprehensive survey of data mining-based fraud detection research. arXiv preprint arXiv:1009.6119.
[3] West, J., & Bhattacharya, M. (2016). Intelligent financial fraud detection: a comprehensive review. Computers & security, 57, 47-66.
[4] Fiore, U., De Santis, A., Perla, F., Zanetti, P., & Palmieri, F. (2019). Using generative adversarial networks for improving classification effectiveness in credit card fraud detection. Information Sciences, 479, 448-455.
[5] Jurgovsky, J., Granitzer, M., Ziegler, K., Calabretto, S., Portier, P. E., He-Guelton, L., & Caelen, O. (2018). Sequence classification for credit-card fraud detection. Expert systems with applications, 100, 234-245.
[6] Chalapathy, R., & Chawla, S. (2019). Deep learning for anomaly detection: A survey. arXiv preprint arXiv:1901.03407.
[7] Srivastava, A., Kundu, A., Sural, S., & Majumdar, A. (2008). Credit card fraud detection using a hidden Markov model. IEEE Transactions on dependable and secure computing, 5(1), 37-48.
[8] Ngai, E. W., Hu, Y., Wong, Y. H., Chen, Y., & Sun, X. (2011). The application of data mining techniques in financial fraud detection: A classification framework and an academic review of literature. Decision support systems, 50(3), 559-569.
[9] Ali, I., Aurangzeb, K., Awais, M., & Aslam, S. (2020, November). An efficient credit card fraud detection system using deep-learning-based approaches. In 2020 IEEE 23rd International Multitopic Conference (INMIC) (pp. 1-6). IEEE.
[10] Thejas, G. S., Dheeshjith, S., Iyengar, S. S., Sunitha, N. R., & Badrinath, P. (2021). A hybrid and effective learning approach for click fraud detection. Machine Learning with Applications, 3, 100016.
[11] Rehman, A., Naz, S., Razzak, M. I., Akram, F., & Imran, M. (2020). A deep learning-based framework for automatic brain tumour classification using transfer learning. Circuits, Systems, and Signal Processing, 39(2), 757-775.
[12] Akhilomen, J. (2013). Data mining application for a cyber credit-card fraud detection system. In Advances in Data Mining. Applications and Theoretical Aspects: 13th Industrial Conference, ICDM 2013, New York, NY, USA, July 16-21, 2013. Proceedings 13 (pp. 218-228). Springer Berlin Heidelberg.
[13] Kou, Y., Lu, C. T., Sirwongwattana, S., & Huang, Y. P. (2004, March). Survey of fraud detection techniques. In IEEE International Conference on Networking, sensing and control, 2004 (Vol. 2, pp. 749-754). IEEE.
[14] Raghavan, P., & El Gayar, N. (2019, December). Fraud detection using machine learning and deep learning. In the 2019 International Conference on Computational Intelligence and Knowledge Economy (ICCIKE) (pp. 334-339). IEEE.
[15] Mubalaike, A. M., & Adali, E. (2018, September). Deep learning approach for an intelligent financial fraud detection system. In 2018, 3rd International Conference on Computer Science and Engineering (UBMK) (pp. 598-603). IEEE.
[16] Alghofaili, Y., Albattah, A., & Rassam, M. A. (2020). A financial fraud detection model based on the LSTM deep learning technique. Journal of Applied Security Research, 15(4), 498-516.
[17] Osegi, E. N., & Jumbo, E. F. (2021). Comparative analysis of credit card fraud detection in simulated annealing trained artificial neural network and hierarchical temporal memory. Machine Learning with Applications, 6, 100080.
[18] Ding, L., Fang, W., Luo, H., Love, P. E., Zhong, B., & Ouyang, X. (2018). A deep hybrid learning model to detect unsafe behavior: Integrating convolution neural networks and long short-term memory. Automation in construction, 86, 118-124.
[19] Liu, H., & Lang, B. (2019). Machine learning and deep learning methods for intrusion detection systems: A survey. applied sciences, 9(20), 4396.
[20] Salur, M. U., & Aydin, I. (2020). A novel hybrid deep learning model for sentiment classification. IEEE Access, 8, 58080-58093.
