Abstract
The detection of fraudulent actions has become a major challenge for upholding the integrity of financial systems in today’s complex and ever-changing financial world. This study recommends a novel method for detecting and preventing financial network fraud by combining the strengths of graph analytics and machine learning. To begin, the paper defines financial networks and describes the intricate relationships and transactions that characterize them. The subtle patterns and abnormalities that indicate fraudulent behaviours in these networks are difficult for conventional fraud detection technologies to capture. Using the abundant structural information available in financial graphs, our proposed integration of graph analytics and machine learning fills this void. When it comes to modelling the complex relationships between entities in financial networks, graph analytics provides a natural framework. An exhaustive graph structure is generated, capturing the complex web of relationships, by modelling entities as nodes and monetary transactions as edges. The use of sophisticated graph algorithms allows us to unearth previously unseen patterns and identify outliers that may point to fraudulent behaviour. Machine learning approaches complement graph analytics by providing the capacity to learn complicated patterns from massive datasets. The graph structure, transaction history, and context data are mined using these methods in our method. When graph-derived characteristics are combined with machine learning algorithms, subtle, high-dimensional patterns that could otherwise go undetected might be found. We run trials on real-world financial datasets, contrasting the results with those of more conventional methods, to verify the efficacy of our proposed approach. The outcomes show a considerable improvement in fraud detection accuracy, with fewer false positives. We also demonstrate the model’s flexibility by using an incremental learning framework to account for new forms of fraud. This paper presents a novel approach to tackling the difficulties of financial network fraud detection by combining graph analytics and machine learning. Our method demonstrates a resilient and flexible way to tackle the ever-changing landscape of financial fraud by combining the structural insights of graph analytics with the pattern recognition skills of machine learning.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Smith, A.B., Johnson, C.D., Williams, E.F.: Graph-based anomaly detection for fraud detection in financial networks. J. Financ. Data Sci. 3(2), 156–168 (2021)
Jin, S., Li, W., Wang, F.: Graph convolutional networks for fraud detection in financial transactions. In: Proceedings of the International Conference on Data Mining (ICDM) (2022)
Chen, J., Li, X., Leung, K.S.: Graph neural networks for fraud detection: a deep learning architecture. IEEE Trans. Big Data 6(4), 683–692 (2020)
Li, Y., Zhang, Q., Wang, X.: Variational graph autoencoders for anomaly detection in financial networks. Expert Syst. Appl. 190, 117542 (2023)
Kim, H., Park, J., Lee, D.: Real-time fraud detection in financial networks: an incremental learning approach. ACM Trans. Intell. Syst. Technol. 14(1), 1–21 (2022)
Hajek, P., Abedin. M.Z., Sivarajah, U.: Fraud detection in mobile payment systems using an XGBoost-based framework. Inf. Syst. Front. 1–19 (2022). https://doi.org/10.1007/s10796-022-10346-6
Zhou, H., Chai, H.F., Qiu, M.L.: Fraud detection within bankcard enrollment on mobile device-based payment using machine learning. Front. Inf. Technol. Electron. Eng. 19, 1537–1545 (2018). https://doi.org/10.1631/FITEE.1800580
Benchaji, I., Douzi, S., Ouahidi, B.E., Jaafari, J.: Enhanced credit card fraud detection based on attention mechanism and LSTM deep model. J. Big Data 8, 1–21 (2021). https://doi.org/10.1186/s40537-021-00541-8
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. 1 (2020). https://doi.org/10.1609/aaai.v34i01.5371
Varalakshmi, A., Santhosh Kumar, S., Shanmugapriya, M.M., Mohanapriya, G., Anand, M.C.J.: Markers location monitoring on images from an infrared camera using optimal fuzzy inference system. Int. J. Fuzzy Syst. 25, 731–742 (2023). https://doi.org/10.1007/s40815-022-01407-8
Bharatraj, J., Anand, M.C.J.: Power harmonic weighted aggregation operator on single-valued trapezoidal neutrosophic numbers and interval-valued neutrosophic sets. In: Kahraman, C., Otay, İ. (eds.) Fuzzy Multi-criteria Decision-Making Using Neutrosophic Sets. Studies in Fuzziness and Soft Computing, LNCS, vol. 369, pp. 45–62. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-00045-5_3
Anand, M.C.J., Bharatraj, J.: Interval-valued neutrosophic numbers with WASPAS. In: Kahraman, C., Otay, I. (eds.) Fuzzy Multi-criteria Decision-Making Using Neutrosophic Sets. Studies in Fuzziness and Soft Computing, LNCS, vol. 369, pp. 435–453. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-00045-5_17
Anand, M.C.J., Bharatraj, J.: Gaussian qualitative trigonometric functions in a fuzzy circle. Adv. Fuzzy Syst. 2018, 1–9 (2018). https://doi.org/10.1155/2018/8623465
Anand, M.C.J., Bharatraj, J.: Theory of triangular fuzzy number. In: Proceedings of NCATM – 2017, pp. 80–83 (2017)
Miriam, M.R., Martin, N., Anand, M.C.J.: Inventory model promoting smart production system with zero defects. Int. J. Appl. Comput. Math. 9 (2023). https://doi.org/10.1007/s40819-023-01524-4
Devadoss, A.V., Anand, M.C.J., Felix, A.: A CETD matrix approach to analyze the dimensions of the personality of a person. In: 2014 International Conference on Computational Science and Computational Intelligence. IEEE (2014). https://ieeexplore.ieee.org/abstract/document/6822301
Anand, M.C.J., Moorthy, C.B., Sivamani, S., Indrakumar, S., Kalaiarasi, K., Barhoi, A.: Fuzzy intelligence inventory decision optimization model of sustainability and green technologies for mixed uncertainties of carbon emission. In: 2023 International Conference on Information Management (ICIM). IEEE (2023). https://ieeexplore.ieee.org/document/10145085
Anand, M.C.J., Martin, N., Clementking, A., Rani, S., Priyadharshini, S., Siva, S.: Decision making on optimal selection of advertising agencies using machine learning. In: 2023 International Conference on Information Management (ICIM). IEEE (2023). https://ieeexplore.ieee.org/document/10145172
Raj, P.J., Prabhu, V.V., Krishnakumar, V., Anand. M.C.J.: Solar powered charging of fuzzy logic controller (FLC) strategy with battery management system (BMS) method used for electric vehicle (EV). Int. J. Fuzzy Syst. (2023). https://doi.org/10.1007/s40815-023-01537-7
Prabha, S.K., et al.: Sorting out interval valued neutrosophic fuzzy shortest cycle route problem by reduced matrix method. Int. J. Neutrosophic Sci. 23(2), 91–103 (2024). https://doi.org/10.54216/IJNS.230208
Kungumaraj, E., et al.: Neutrosophic topological vector spaces and its properties. Int. J. Neutrosophic Sci. 23(2), 63–76 (2024). https://doi.org/10.54216/IJNS.230206
Rajesh, K., et al.: A study on interval valued temporal neutrosophic fuzzy sets. Int. J. Neutrosophic Sci. 23(1), 341–349 (2024). https://doi.org/10.54216/IJNS.230129
Manshath, A., et al.: Neutrosophic integrals by reduction formula and partial fraction methods for indefinite integrals. Int. J. Neutrosophic Sci. 23(1), 08–16 (2024). ISSN: 2690-6805. https://doi.org/10.54216/IJNS.230101
Sudha, S., Martin, N., Anand, M.C.J., Palanimani, P.G., Thirunamakkani, T., Ranjitha, B.: MACBETH-MAIRCA plithogenic decision-making on feasible strategies of extended producer’s responsibility towards environmental sustainability. Int. J. Neutrosophic Sci. 22(2), 114–130 (2023). ISSN: 2690-6805. https://doi.org/10.54216/IJNS.220210
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Nagaraj, C., Anand, M.C.J., Priyadharshini, S.S., Aparna, P. (2024). GCNXG: Detecting Fraudulent Activities in Financial Networks: A Graph Analytics and Machine Learning Fusion. In: Gundebommu, S.L., Sadasivuni, L., Malladi, L.S. (eds) Renewable Energy, Green Computing, and Sustainable Development. REGS 2023. Communications in Computer and Information Science, vol 2081. Springer, Cham. https://doi.org/10.1007/978-3-031-58607-1_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-58607-1_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-58606-4
Online ISBN: 978-3-031-58607-1
eBook Packages: EnergyEnergy (R0)