Unsupervised Credit Card Fraud Detection Using Autoencoder-Based Anomaly Detection on Highly Imbalanced Transaction Data
DOI:
https://doi.org/10.64479/iarci.v1i2.64Keywords:
credit card fraud detection, anomaly detection, autoencoder, unsupervised learning, imbalanced data, reconstruction errorAbstract
Credit card fraud detection is a critical problem in the financial sector, primarily due to its direct correlation with financial liability and the preservation of user integrity. A major challenge in fraud detection is the extreme class imbalance, where fraudulent transactions are rare compared to legitimate ones, causing supervised approaches to require sufficient labeled fraud data and often become biased toward the majority class. This study proposes an unsupervised anomaly detection approach based on an Autoencoder to identify fraudulent transactions in highly imbalanced credit card transaction data. The Autoencoder is trained exclusively on normal transactions to learn representative patterns of legitimate behavior. During inference phase, transactions exhibiting elevated reconstruction error relative to established norms are designated as anomalies, indicative of potential fraud. The experiments use the Credit Card Fraud Detection dataset from Kaggle, containing 284,807 transactions: 284,315 normal (99.828%) and 492 fraudulent (0.172%). The workflow includes numerical feature normalization for the Time and Amount attributes, splitting normal data into training and validation sets, selecting an anomaly threshold based on the reconstruction error distribution, and evaluating performance using metrics suitable for imbalanced data such as precision, recall, and F1-score. The results indicate that the proposed unsupervised Autoencoder offers an effective alternative when labeled fraud examples are limited, by detecting deviations from normal transaction patterns through reconstruction behavior.
Downloads
References
[1] N. Rosley, G. Tong, K. Ng, S. Kalid, and K. Khor, “Autoencoders with Reconstruction Error and Dimensionality Reduction for Credit Card Fraud Detection,” J. Syst. Manag. Sci., 2022, doi: 10.33168/jsms.2022.0605.
[2] H. Fanai and H. Abbasimehr, “A novel combined approach based on deep Autoencoder and deep classifiers for credit card fraud detection,” Expert Syst. Appl., vol. 217, p. 119562, 2023, doi: 10.1016/j.eswa.2023.119562.
[3] L. Ding, L. Liu, Y. Wang, P. Shi, and J. Yu, “An AutoEncoder enhanced light gradient boosting machine method for credit card fraud detection,” PeerJ Comput. Sci., vol. 10, 2024, doi: 10.7717/peerj-cs.2323.
[4] S. Jiang, R. Dong, J. Wang, and M. Xia, “Credit Card Fraud Detection Based on Unsupervised Attentional Anomaly Detection Network,” Systems, vol. 11, p. 305, 2023, doi: 10.3390/systems11060305.
[5] M. Shanaa and S. Abdallah, “A Hybrid Anomaly Detection Framework Combining Supervised and Unsupervised Learning for Credit Card Fraud Detection,” F1000Research, 2025, doi: 10.12688/f1000research.166350.1.
[6] H. Du, L. Lv, A. Guo, and H. Wang, “AutoEncoder and LightGBM for Credit Card Fraud Detection Problems,” Symmetry (Basel)., vol. 15, p. 870, 2023, doi: 10.3390/sym15040870.
[7] J. Adejoh, N. Owoh, M. Ashawa, S. Hosseinzadeh, A. Shahrabi, and S. Mohamed, “An Adaptive Unsupervised Learning Approach for Credit Card Fraud Detection,” Big Data Cogn. Comput., vol. 9, p. 217, 2025, doi: 10.3390/bdcc9090217.
[8] I. Mienye and Y. Sun, “A Deep Learning Ensemble With Data Resampling for Credit Card Fraud Detection,” IEEE Access, vol. 11, pp. 30628–30638, 2023, doi: 10.1109/access.2023.3262020.
[9] A. Mitra, M. Siddhant, and G. P, “Credit Card Fraud Detection using Autoencoders,” YMER Digit., 2022, doi: 10.37896/ymer21.06/32.
[10] M. Vardhan, M. Ankitha, P. Sri, M. Battula, and M. Priyanka, “Anomaly Detection in Credit Card Transactions using Autoencoders,” IJARCCE, 2024, doi: 10.17148/ijarcce.2024.13320.
[11] D. Yaganti, “Unsupervised Deep Learning for Credit Card Fraud Detection: An Autoencoder-Driven Framework with Real-Time Dash Visualization Using Tensorflow 2.X,” Int. J. Adv. Res. Sci. Commun. Technol., 2023, doi: 10.48175/ijarsct-11978t.
[12] F. Alshameri and R. Xia, “An Evaluation of Variational Autoencoder in Credit Card Anomaly Detection,” Big Data Min. Anal., vol. 7, pp. 718–729, 2024, doi: 10.26599/bdma.2023.9020035.
[13] O. Kilickaya, “Hybrid Explainable Autoencoders for Credit Card Fraud Detection: Integrating Deep Latent Representations with Model-Agnostic Interpretability,” in Proceedings of the 2025 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA), 2025, pp. 1–7. doi: 10.1109/acdsa65407.2025.11166201.
[14] R. Kumar and S. Kiran, “AI-Driven Frameworks for Unsupervised Fraud Detection in Banking Cybersecurity,” Int. J. Sci. Eng. Appl., 2025, doi: 10.7753/ijsea1403.1006.
[15] F. Alarfaj and S. Shahzadi, “Enhancing Fraud Detection in Banking With Deep Learning: Graph Neural Networks and Autoencoders for Real-Time Credit Card Fraud Prevention,” IEEE Access, vol. 13, pp. 20633–20646, 2025, doi: 10.1109/access.2024.3466288.
[16] M. Aich, V. Oggu, M. Sankaran, K. K, and Z. Sataar, “An Integrated Temporal Graph Neural Network and Autoencoder Model for Real-Time Credit Card Fraud Detection,” in 2025 2nd International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS), 2025, pp. 1–6. doi: 10.1109/iacis65746.2025.11210970.
[17] A. 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, p. 6, 2024, doi: 10.3390/bdcc8010006.
[18] I. Mienye, E. Esenogho, and C. Modisane, “Detecting Imbalanced Credit Card Fraud via Hybrid Graph Attention and Variational Autoencoder Ensembles,” Appl. Math., 2025, doi: 10.3390/appliedmath5040131.
[19] L. Bonde and A. Bichanga, “Improving Credit Card Fraud Detection with Ensemble Deep Learning-Based Models: A Hybrid Approach Using SMOTE-ENN,” J. Comput. Theor. Appl., 2025, doi: 10.62411/jcta.12021.
[20] E. Ileberi and Y. Sun, “A Hybrid Deep Learning Ensemble Model for Credit Card Fraud Detection,” IEEE Access, vol. 12, pp. 175829–175838, 2024, doi: 10.1109/access.2024.3502542.
[21] J. Akshay, T. Vinusha, R. Bianca, C. Krishna, and G. Radhika, “Enhancing Credit Card Fraud Detection with Deep Learning and Graph Neural Networks,” in 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), 2024, pp. 1–6. doi: 10.1109/icccnt61001.2024.10725042.
[22] S. Shinde and S. Kale, “Unveiling Anomalies in Credit Card Transactions using Autoencoder Neural Networks,” Int. Adv. Res. J. Sci. Eng. Technol., 2023.
[23] M. Al-Shabi, “Credit Card Fraud Detection Using Autoencoder Model in Unbalanced Datasets,” J. Adv. Math. Comput. Sci., 2019.
[24] C. Huot, S. Heng, T.-K. Kim, and Y. Han, “Quantum Autoencoder for Enhanced Fraud Detection in Imbalanced Credit Card Dataset,” IEEE Access, 2024.
