LEVERAGING ARTIFICIAL INTELLIGENCE AND BIG DATA ANALYTICS TO DETECT CIRCULAR TRADING AND TAX EVASION IN GST TRANSACTIONS
DOI:
https://doi.org/10.59415/mjacs.370Keywords:
GST, Circular Trading, Artificial Intelligence, Big Data Analytics, Graph Neural Networks, Fraud DetectionAbstract
This study presents a data-driven framework employing Artificial Intelligence (AI) and Big Data techniques to address circular trading and tax evasion in India’s Goods and Services Tax (GST) system. By representing transactions as a directed graph and integrating multi-source data, including e-way bill records and invoice metadata, the framework applies advanced learning models such as Graph Neural Networks (GNNs), anomaly detection algorithms, and gradient-boosted classifiers to identify suspicious patterns in near real-time. The methodology encompasses graph construction, feature engineering, and risk scoring with an emphasis on temporal motifs and logistics anomalies to enhance detection precision. Comparative experiments demonstrate that the proposed approach significantly improves fraud detection accuracy over rule-based methods while providing interpretable outputs for enforcement agencies. The study concludes with recommendations for large-scale deployment within the national GST analytics infrastructure, highlighting opportunities for real-time processing and privacy-preserving machine learning approaches.
Downloads
References
[1] A. Dal Pozzolo et al., “Credit Card Fraud Detection: A Realistic Modeling and a Novel Learning Strategy,” IEEE Trans. Neural Netw. Learn. Syst., vol. 29, no. 8, pp. 3784–3797, 2018. DOI: https://doi.org/10.1109/TNNLS.2017.2736643
[2] R. J. Bolton and D. J. Hand, “Statistical Fraud Detection: A Review,” Statistical Science, vol. 17, no. 3, pp. 235–255, 2002. DOI: https://doi.org/10.1214/ss/1042727940
[3] M. Girvan and M. E. J. Newman, “Community Structure in Social and Biological Networks,” Proc. Natl. Acad. Sci. USA, vol. 99, no. 12, pp. 7821–7826, 2002. DOI: https://doi.org/10.1073/pnas.122653799
[4] L. Akoglu, H. Tong, and D. Koutra, “Graph-based Anomaly Detection and Description: A Survey,” Data Mining and Knowledge Discovery, vol. 29, no. 3, pp. 626–688, 2015. DOI: https://doi.org/10.1007/s10618-014-0365-y
[5] Z. Wu et al., “A Comprehensive Survey on Graph Neural Networks,” IEEE Trans. Neural Netw. Learn. Syst., vol. 32, no. 1, pp. 4–24, 2021. DOI: https://doi.org/10.1109/TNNLS.2020.2978386
[6] F. T. Liu, K. M. Ting, and Z.-H. Zhou, “Isolation Forest,” in Proc. ICDM, 2008, pp. 413–422. DOI: https://doi.org/10.1109/ICDM.2008.17
[7] M. M. Breunig et al., “LOF: Identifying Density-Based Local Outliers,” in Proc. ACM SIGMOD, 2000, pp. 93–104. DOI: https://doi.org/10.1145/342009.335388
[8] J. An and S. Cho, “Variational Autoencoder based Anomaly Detection using Reconstruction Probability,” Special Lecture on IE, vol. 2, no. 1, pp. 1–18, 2015.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Panish Kumar K C, Manasa.S
This work is licensed under a Creative Commons Attribution 4.0 International License.
License Statement
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
Authors who publish with mLAC Journal for Arts, Commerce and Sciences (m-JACS) retain copyright of their articles and grant the journal the right of first publication.
This license allows others to share, use, and build upon the work—commercially or non-commercially—as long as appropriate credit is given to the original authors and source, and any changes are indicated.
The journal encourages open access and supports the free exchange of knowledge while ensuring proper attribution of original work.
