AI-Based Fraud Detection Employing Graph Structures and Advanced Anomaly Modeling Techniques
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V4I3P112Keywords:
Fraud Detection, Graph-Based Learning, Anomaly Detection, Artificial Intelligence, Graph Neural Networks, Financial Security, Machine LearningAbstract
Criminal acts are becoming more sophisticated as digital financial ecosystems, Internet transactions, and interdependent cyber-physical networks continue to grow rapidly. The limits of traditional methods of fraud detection The conventional approach to fraud detection mostly relies on rule-detection systems and classical machine learning frameworks, can hardly accommodate all the emerging trends of fraud, multidimensional data, and relational networks between the entities. Graph-based learning, and anomaly modeling approaches to Artificial Intelligence (AI) has become a prospective well-established and scalable method of detecting fraud in recent years. The present paper provides a thorough research on AI-based fraud detection models utilizing graph structures with complex anomaly detecting models. Graph representations allow modeling of all of the relationships between users, transactions, devices and accounts explicitly and thus capture all structural dependencies that are frequent with traditional methods. More important features are advanced anomaly modeling methods, such as statistical and machine learning-based methods, and deep learning-based methods, which increase the capacity of the system to detect unnoticed before fraudulent behaviors. This paper reviews the body of available literature systematically, pinpoints the weaknesses in the conventional and recent methods, and presents a generalized approach to the methodology taking advantage of graph theory, graph neural networks (GNNs), and hybrid anomaly detecting models. The suggested structure focuses on scalability, adaptability and explainability which are major requirements of real-life fraud detection systems. A large-scale literature on experimental analysis with benchmark datasets of fraud on graphs proves that the graph-based anomaly modeling model significantly outperforms the baseline models in the following metrics: discrimination accuracy, accuracy and the ability to recall as well as ability to survive concept drift. The findings suggest the paramount role of relational learning and anomaly-based modeling in dealing with modern-day fraud issues. The paper will end with the discussion of the implications to practice, limitations, and future research in AI-powered fraud detection systems
References
[1] Bolton, R. J., & Hand, D. J. (2002). Statistical fraud detection: A review. Statistical science, 17(3), 235-255.
[2] Fawcett, T., & Provost, F. (1997). Adaptive fraud detection. Data mining and knowledge discovery, 1(3), 291-316.
[3] Hand, D. J. (2006). Classifier technology and the illusion of progress.
[4] 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.
[5] Phua, C., Lee, V., Smith, K., & Gayler, R. (2010). A comprehensive survey of data mining-based fraud detection research. arXiv preprint arXiv:1009.6119.
[6] Kantchelian, A., Afroz, S., Huang, L., Islam, A. C., Miller, B., Tschantz, M. C., ... & Tygar, J. D. (2013, November). Approaches to adversarial drift. In Proceedings of the 2013 ACM workshop on Artificial intelligence and security (pp. 99-110).
[7] Liu, F. T., Ting, K. M., & Zhou, Z. H. (2008, December). Isolation forest. In 2008 eighth ieee international conference on data mining (pp. 413-422). IEEE.
[8] Breunig, M. M., Kriegel, H. P., Ng, R. T., & Sander, J. (2000, May). LOF: identifying density-based local outliers. In Proceedings of the 2000 ACM SIGMOD international conference on Management of data (pp. 93-104).
[9] An, J., & Cho, S. (2015). Variational autoencoder based anomaly detection using reconstruction probability. Special lecture on IE, 2(1), 1-18.
[10] Akoglu, L., Tong, H., & Koutra, D. (2015). Graph based anomaly detection and description: a survey. Data mining and knowledge discovery, 29(3), 626-688.
[11] Hooi, B., Song, H. A., Beutel, A., Shah, N., Shin, K., & Faloutsos, C. (2016, August). Fraudar: Bounding graph fraud in the face of camouflage. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (pp. 895-904).
[12] Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., & Mei, Q. (2015, May). Line: Large-scale information network embedding. In Proceedings of the 24th international conference on world wide web (pp. 1067-1077).
[13] Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2020). A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems, 32(1), 4-24.
[14] Al Garadi, M. A., Mohamed, A., & Al Ali, A. K. (2020). Deep and machine learning approaches for anomaly based intrusion detection of IoT systems: A review. IEEE Communications Surveys & Tutorials, 22(1), 106–139. https://doi.org/10.1109/COMST.2019.2958727
[15] Pourhabibi, T., Ong, K. L., Kam, B. H., & Boo, Y. L. (2020). Fraud detection: A systematic literature review of graph-based anomaly detection approaches. Decision Support Systems, 133, 113303.
[16] Celestin, M., & Vanitha, N. (2019). Artificial intelligence in fraud detection: Are traditional auditing methods outdated. In 2nd International Conference on Recent Trends in Arts, Science, Engineering & Technology (Vol. 3, No. 2, pp. 180-186).
[17] del Mar Roldán-García, M., García-Nieto, J., & Aldana-Montes, J. F. (2017). Enhancing semantic consistency in anti-fraud rule-based expert systems. Expert Systems with Applications, 90, 332-343.
[18] Behdad, M., Barone, L., Bennamoun, M., & French, T. (2012). Nature-inspired techniques in the context of fraud detection. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 42(6), 1273-1290.
[19] Wiese, B., & Omlin, C. (2009). Credit card transactions, fraud detection, and machine learning: Modelling time with LSTM recurrent neural networks. In Innovations in neural information paradigms and applications (pp. 231-268). Berlin, Heidelberg: Springer Berlin Heidelberg.
[20] Li, R., Liu, Z., Ma, Y., Yang, D., & Sun, S. (2022). Internet financial fraud detection based on graph learning. IEEE Transactions on Computational Social Systems, 10(3), 1394-1401.
[21] Nangi, P. R., Obannagari, C. K. R. N., & Settipi, S. (2022). Enhanced Serverless Micro-Reactivity Model for High-Velocity Event Streams within Scalable Cloud-Native Architectures. International Journal of Emerging Research in Engineering and Technology, 3(3), 127-135. https://doi.org/10.63282/3050-922X.IJERET-V3I3P113
[22] Bhat, J., & Sundar, D. (2022). Building a Secure API-Driven Enterprise: A Blueprint for Modern Integrations in Higher Education. International Journal of Emerging Research in Engineering and Technology, 3(2), 123-134. https://doi.org/10.63282/3050-922X.IJERET-V3I2P113
[23] Jayaram, Y., & Sundar, D. (2022). Enhanced Predictive Decision Models for Academia and Operations through Advanced Analytical Methodologies. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 3(4), 113-122. https://doi.org/10.63282/3050-9262.IJAIDSML-V3I4P113
[24] Nangi, P. R., Obannagari, C. K. R. N., & Settipi, S. (2022). Self-Auditing Deep Learning Pipelines for Automated Compliance Validation with Explainability, Traceability, and Regulatory Assurance. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 3(1), 133-142. https://doi.org/10.63282/3050-9262.IJAIDSML-V3I1P114
[25] Jayaram, Y., Sundar, D., & Bhat, J. (2022). AI-Driven Content Intelligence in Higher Education: Transforming Institutional Knowledge Management. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 3(2), 132-142. https://doi.org/10.63282/3050-9262.IJAIDSML-V3I2P115
[26] Nangi, P. R., Reddy Nala Obannagari, C. K., & Settipi, S. (2022). Predictive SQL Query Tuning Using Sequence Modeling of Query Plans for Performance Optimization. International Journal of AI, BigData, Computational and Management Studies, 3(2), 104-113. https://doi.org/10.63282/3050-9416.IJAIBDCMS-V3I2P111
[27] Bhat, J. (2022). The Role of Intelligent Data Engineering in Enterprise Digital Transformation. International Journal of AI, BigData, Computational and Management Studies, 3(4), 106-114. https://doi.org/10.63282/3050-9416.IJAIBDCMS-V3I4P111
[28] Jayaram, Y., & Bhat, J. (2022). Intelligent Forms Automation for Higher Ed: Streamlining Student Onboarding and Administrative Workflows. International Journal of Emerging Trends in Computer Science and Information Technology, 3(4), 100-111. https://doi.org/10.63282/3050-9246.IJETCSIT-V3I4P110
