Abstract
The fraud detection literature unanimously shows that the use of a cardholder’s transaction history as context improves the classification of the current transaction. Context representation is usually performed through either of two approaches. The first, manual feature engineering, is expensive, restricted, and hard to maintain as it relies on human expertise. The second, automatic context representation, removes the human dependency by learning new features directly on the fraud data with an end-to-end neural network. The LSTM and the more recent Neural Feature Aggregate Generator (NAG) are examples of such an approach. The architecture of the NAG is inspired by manual feature aggregates and addresses several of their limitations, primarily because it is automatic. However, it still has several drawbacks that we aim to address in this paper. In particular, we propose to extend the NAG in the following two main manners: (1) By expanding its expressiveness to model a larger panel of functions and constraints. This includes the possibility to model time constraints and additional aggregation functions. (2) By better aligning its architecture with the domain expert intuition on feature aggregates. We evaluate the different extensions of the NAG through a series of experiments on a real-world credit-card dataset consisting of over 60 million transactions. The extensions show comparable performance to the NAG on the fraud-detection task, while providing additional benefits in terms of model size and interpretability.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
APATE: A novel approach for automated credit card transaction fraud detection using network-based extensions. Decis. Support Syst. 75, 38–48 (2015). https://doi.org/10.1016/j.dss.2015.04.013. https://www.sciencedirect.com/science/article/pii/S0167923615000846
How artificial intelligence and machine learning research impacts payment card fraud detection: a survey and industry benchmark. Eng. Appl. Artif. Intell. 76, 130–157 (2018). https://doi.org/10.1016/j.engappai.2018.07.008. https://www.sciencedirect.com/science/article/pii/S0952197618301520
Alazizi, A., Habrard, A., Jacquenet, F., He-Guelton, L., Oblé, F., Siblini, W.: Anomaly detection, consider your dataset first an illustration on fraud detection. In: 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), pp. 1351–1355 (2019). https://doi.org/10.1109/ICTAI.2019.00188
Awoyemi, J.O., Adetunmbi, A.O., Oluwadare, S.A.: Credit card fraud detection using machine learning techniques: a comparative analysis. In: 2017 International Conference on Computing Networking and Informatics (ICCNI), pp. 1–9 (2017). https://doi.org/10.1109/ICCNI.2017.8123782
Cheng, D., Xiang, S., Shang, C., Zhang, Y., Yang, F., Zhang, L.: Spatio-temporal attention-based neural network for credit card fraud detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 01, pp. 362–369 (2020)
Correa Bahnsen, A., Aouada, D., Stojanovic, A., Ottersten, B.: Feature engineering strategies for credit card fraud detection. Expert Syst. Appl. 51, 134–142 (2016)
Dal Pozzolo, A.: Adaptive machine learning for credit card fraud detection (2015)
Dal Pozzolo, A., Boracchi, G., Caelen, O., Alippi, C., Bontempi, G.: Credit card fraud detection and concept-drift adaptation with delayed supervised information. In: 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1–8 (2015). https://doi.org/10.1109/IJCNN.2015.7280527
Fiore, U., De Santis, A., Perla, F., Zanetti, P., Palmieri, F.: Using generative adversarial networks for improving classification effectiveness in credit card fraud detection. Inf. Sci. 479, 448–455 (2019)
Forough, J., Momtazi, S.: Sequential credit card fraud detection: a joint deep neural network and probabilistic graphical model approach. Expert Syst. e12795. https://doi.org/10.1111/exsy.12795. https://onlinelibrary.wiley.com/doi/abs/10.1111/exsy.12795
Ghosh Dastidar, K., Jurgovsky, J., Siblini, W., Granitzer, M.: NAG: neural feature aggregation framework for credit card fraud detection. Knowl. Inf. Syst. 64(3), 831–858 (2022)
Ghosh Dastidar, K., Jurgovsky, J., Siblini, W., He-Guelton, L., Granitzer, M.: NAG: neural feature aggregation framework for credit card fraud detection. In: 2020 IEEE International Conference on Data Mining (ICDM), pp. 92–101 (2020). https://doi.org/10.1109/ICDM50108.2020.00018
Hordri, N.F., Yuhaniz, S.S., Azmi, N.F.M., Shamsuddin, S.M.: Handling class imbalance in credit card fraud using resampling methods. Int. J. Adv. Comput. Sci. Appl. 9(11) (2018). https://doi.org/10.14569/IJACSA.2018.091155
Jurgovsky, J., et al.: Sequence classification for credit-card fraud detection. Expert Syst. Appl. 100, 234–245 (2018)
Kim, E., et al.: Champion-challenger analysis for credit card fraud detection: hybrid ensemble and deep learning. Expert Syst. Appl. 128, 214–224 (2019). https://doi.org/10.1016/j.eswa.2019.03.042. https://www.sciencedirect.com/science/article/pii/S0957417419302167
Lucas, Y., Jurgovsky, J.: Credit card fraud detection using machine learning: a survey (2020)
Lucas, Y., et al.: Multiple perspectives hmm-based feature engineering for credit card fraud detection. In: Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing, SAC 2019, pp. 1359–1361. Association for Computing Machinery, New York (2019). https://doi.org/10.1145/3297280.3297586
Lucas, Y., et al.: Dataset shift quantification for credit card fraud detection. In: 2019 IEEE Second International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), pp. 97–100 (2019). https://doi.org/10.1109/AIKE.2019.00024
Ozenne, B., Subtil, F., Maucort-Boulch, D.: The precision-recall curve overcame the optimism of the receiver operating characteristic curve in rare diseases. J. Clin. Epidemiol. 68(8), 855–859 (2015). https://pubmed.ncbi.nlm.nih.gov/25881487/
Pumsirirat, A., Yan, L.: Credit card fraud detection using deep learning based on auto-encoder and restricted Boltzmann machine. Int. J. Adv. Comput. Sci. Appl. 9(1), 18–25 (2018)
Randhawa, K., Loo, C.K., Seera, M., Lim, C.P., Nandi, A.K.: Credit card fraud detection using adaboost and majority voting. IEEE Access 6, 14277–14284 (2018). https://doi.org/10.1109/ACCESS.2018.2806420
Russac, Y., Caelen, O., He-Guelton, L.: Embeddings of categorical variables for sequential data in fraud context. In: Hassanien, A.E., Tolba, M.F., Elhoseny, M., Mostafa, M. (eds.) AMLTA 2018. AISC, vol. 723, pp. 542–552. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-74690-6_53
Whitrow, C., Hand, D.J., Juszczak, P., Weston, D., Adams, N.M.: Transaction aggregation as a strategy for credit card fraud detection. Data Min. Knowl. Discov. 18(1), 30–55 (2009)
Xuan, S., Liu, G., Li, Z., Zheng, L., Wang, S., Jiang, C.: Random forest for credit card fraud detection. In: 2018 IEEE 15th International Conference on Networking, Sensing and Control (ICNSC), pp. 1–6 (2018). https://doi.org/10.1109/ICNSC.2018.8361343
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ghosh Dastidar, K., Siblini, W., Granitzer, M. (2023). Expressive and Intuitive Models for Automated Context Representation Learning in Credit-Card Fraud Detection. In: Nicosia, G., et al. Machine Learning, Optimization, and Data Science. LOD 2022. Lecture Notes in Computer Science, vol 13811. Springer, Cham. https://doi.org/10.1007/978-3-031-25891-6_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-25891-6_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25890-9
Online ISBN: 978-3-031-25891-6
eBook Packages: Computer ScienceComputer Science (R0)