AI-Driven Multi-Document Correlation Framework for Enterprise Financial Compliance and Fraud Detection
Keywords:
Multi-Document Correlation, Financial Fraud Detection, Probabilistic Risk Modeling, Cross-Jurisdictional Normalization, Compliance AutomationAbstract
Enterprise financial compliance has become one of the most technically demanding functions in modern organizations, shaped by the convergence of multi-jurisdictional regulatory obligations, growing transaction volumes, and increasingly adaptive fraud tactics. Existing compliance architectures, built on deterministic rule engines and document-level validation, are structurally ill-equipped to detect inconsistencies that emerge across related financial records rather than within them. A salary discrepancy between a payroll file and a tax return, or a vendor identifier that resolves differently across an invoice and a procurement record, represents precisely the class of anomaly that single-document processing cannot surface. This article proposes a multi-document correlation framework that addresses this structural limitation. Unlike document-level validation or NLP-based entity extraction, the framework performs cross-document relational fraud detection through probabilistic signal aggregation. The architecture has three integrated components: a graph-based entity correlation engine that links payroll, tax, transactional, and procurement records; an adaptive probabilistic risk model that combines cross-document anomaly signals into prioritized audit intelligence; and a cross-jurisdictional normalization layer that allows consistent comparison of financial data across different regulatory environments. The framework is proposed for enterprise-level deployment. Evaluation against rule-based and NLP-augmented baselines demonstrates improvements in fraud detection precision (~91%), a ~76% reduction in false positives, and a ~40% reduction in manual review volume. Collectively, the framework repositions compliance from a reactive audit function into a continuous, predictive governance capability.
Downloads
References
Victoria Hodge and Jim Austin, "A survey of outlier detection methodologies," Artificial Intelligence Review, 2004. Available: https://eprints.whiterose.ac.uk/id/eprint/767/1/hodgevj4.pdf
Eric WT Ngai et al., "The application of data mining techniques in financial fraud detection: A classification framework and an academic review of literature," Decision Support Systems, 2011. Available: https://doi.org/10.1016/j.dss.2010.08.006
Richard J. Bolton and David J. Hand, "Statistical fraud detection: A review," Statistical Science, 2002. Available: https://projecteuclid.org/journals/statistical-science/volume-17/issue-3/Statistical-Fraud-Detection-A-Review/10.1214/ss/1042727940.pdf
Charu C. Aggarwal, "Outlier ensembles," in Outlier Analysis, Springer International Publishing, 2016. Available: https://www.charuaggarwal.net/ensembles.pdf
Raghavendra Chalapathy and Sanjay Chawla, "Deep learning for anomaly detection: A survey," arXiv preprint arXiv:1901.03407, 2019. Available: https://arxiv.org/pdf/1901.03407
Ian Goodfellow et al., “Deep Learning,” MIT Press, 2016. Available: https://synapse.koreamed.org/pdf/10.4258/hir.2016.22.4.351
Jacob Devlin et al., "BERT: Pre-training of deep bidirectional transformers for language understanding," Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019. Available: https://aclanthology.org/N19-1423.pdf
Yinhan Liu et al., "RoBERTa: A robustly optimized BERT pretraining approach," arXiv preprint arXiv:1907.11692, 2019. Available: https://arxiv.org/pdf/1907.11692
Anoop R. Katti et al., "Chargrid: Towards understanding 2D documents," Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018. Available: https://aclanthology.org/D18-1476.pdf
Basel Committee, "Principles for the sound management of operational risk," Bank for International Settlements, 2011. Available: https://www.bis.org/publ/bcbs195.pdf
Financial Action Task Force (FATF), "Guidance for a risk-based approach: The banking sector," FATF/OECD, 2014. Available: https://www.fatf-gafi.org/content/dam/fatf-gafi/guidance/Guidance-Financial-Inclusion%20-Anti-Money-Laundering-Terrorist-Financing-Measures.pdf.coredownload.pdf
Tianqi Chen and Carlos Guestrin, "XGBoost: A scalable tree boosting system," Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016. Available: https://dl.acm.org/doi/pdf/10.1145/2939672.2939785
Ivan P. Fellegi and Alan B. Sunter, "A theory for record linkage," Journal of the American Statistical Association, 1969. Available: https://www2.stat.duke.edu/~rcs46/linkage/presentations/01-baiLi_FelleigSunter1969.pdf
Shaoxiong Ji et al., "A survey on knowledge graphs: Representation, acquisition, and applications," IEEE Transactions on Neural Networks and Learning Systems, 2021. Available: https://www.researchgate.net/publication/351115157
David Savage et al., "Detection of money laundering groups using supervised learning in networks," arXiv preprint arXiv:1608.00708, 2016. Available: https://arxiv.org/pdf/1608.00708
Douglas W. Arner et al., "FinTech, RegTech, and the reconceptualization of financial regulation," Northwestern Journal of International Law and Business, 2016. Available: https://scholarlycommons.law.northwestern.edu/cgi/viewcontent.cgi?article=1817&context=njilb
Scott M. Lundberg and Su-In Lee, "A unified approach to interpreting model predictions," Advances in Neural Information Processing Systems, 2017. Available: https://proceedings.neurips.cc/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf
Brendan McMahan et al., "Communication-efficient learning of deep networks from decentralized data," Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), 2017. Available: https://proceedings.mlr.press/v54/mcmahan17a/mcmahan17a.pdf
Véronique Van Vlasselaer et al., "APATE: A novel approach for automated credit card transaction fraud detection using network-based extensions," Decision Support Systems, 2015. Available: https://www.sciencedirect.com/science/article/pii/S0167923615000846
Yang Liu et al., "Pick and choose: A GNN-based imbalanced learning approach for fraud detection," Proceedings of the Web Conference 2021, 2021. Available: https://dl.acm.org/doi/pdf/10.1145/3442381.3449989
Adetunji Adejumo Paul and Chinonso Ogburie, "The role of AI in preventing financial fraud and enhancing compliance," GSC Advanced Research and Reviews, 2025. Available: https://www.researchgate.net/profile/Chinonso-Ogburie/publication/390300143
Samia Ara Chowdhury et al., "Next generation financial security: Leveraging AI for fraud detection, compliance, and adaptive risk management," Well Testing Journal, 2025. Available: https://www.researchgate.net/publication/394087142
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
