LEVERAGING HYBRID AI FOR REAL-TIME FRAUD DETECTION: A CASE STUDY ON THE EFFICACY OF GRAPH NEURAL NETWORKS AND ANOMALY DETECTION IN NIGERIAN FINTECHS
DOI:
https://doi.org/10.29121/digisecforensics.v2.i2.2025.60Keywords:
Financial Fraud, Fintech, Artificial Intelligence, Graph Neural Networks, Anomaly Detection, Real-Time Systems, Nigeria, Hybrid ModelAbstract
This study investigates the development and application of a hybrid artificial intelligence (AI) model for real-time fraud prevention within Nigeria's rapidly growing FinTech sector. The research addresses the critical challenge of sophisticated financial fraud, which hampers financial inclusion and erodes consumer trust. Moving beyond traditional single-model approaches, this paper proposes a novel framework integrating Graph Neural Networks (GNNs) to analyze complex transactional relationships and an Isolation Forest algorithm for point anomaly detection. Using a real-world, anonymized transaction dataset from a major Nigerian FinTech company, the study trains and validates the hybrid model. Key performance metrics (Precision, Recall, F1-Score, AUC-ROC) are evaluated against benchmark models, including Logistic Regression and Random Forest. The results demonstrate the superior efficacy of the hybrid AI approach, achieving an F1-score of 0.92 and an AUC-ROC of 0.98, significantly outperforming the benchmarks in accurately flagging fraudulent transactions while minimizing false positives. The study concludes that a hybrid model is particularly suited for the unique challenges of the Nigerian FinTech landscape and provides strategic recommendations for the practical integration of such explainable AI systems to bolster security and foster sustainable growth.
References
Bahnsen, A. C., Aouada, D., and Ottersten, B. (2016). Feature Engineering Strategies for Credit Card Fraud Detection. Expert Systems with Applications, 51, 134–142. https://doi.org/10.1016/j.eswa.2015.12.030 DOI: https://doi.org/10.1016/j.eswa.2015.12.030
Central Bank of Nigeria. (2022). Payments System Vision 2025.
Economic and Financial Crimes Commission. (2023). EFCC Annual Report 2022.
Hevner, A. R., March, S. T., Park, J., and Ram, S. (2004). Design Science in Information Systems Research. MIS Quarterly, 28(1), 75–105. https://doi.org/10.2307/25148625 DOI: https://doi.org/10.2307/25148625
Jurgovsky, J., Granitzer, M., Ziegler, K., Calabretto, S., Portier, P. E., He-Guelton, L., and Caelen, O. (2018). Sequence Classification for Credit-Card Fraud Detection. Expert Systems with Applications, 100, 234–245. https://doi.org/10.1016/j.eswa.2018.01.037 DOI: https://doi.org/10.1016/j.eswa.2018.01.037
Liu, F. T., Ting, K. M., and Zhou, Z. H. (2008). Isolation Forest. In Proceedings of the 2008 Eighth IEEE International Conference on Data Mining (pp. 413–422). IEEE. https://doi.org/10.1109/ICDM.2008.17 DOI: https://doi.org/10.1109/ICDM.2008.17
Liu, Y., Li, Z., Zhou, C., Jiang, Y., Sun, J., Wang, M., and He, X. (2021). Generative Adversarial Networks for Anomaly Detection in Financial Time Series. ACM Transactions on Knowledge Discovery from Data, 15(4), Article 60, 1–23.
Pandey, A., Siripurapu, A., and Kumar, S. (2021). A Graph-Based Approach for Financial Fraud Detection. In 2021 IEEE International Conference on Big Data (Big Data) (pp. 1759–1768). IEEE.
Roy, A., Sun, J., Mahoney, R., Alon, L., Jin, M., and Fletcher, T. (2022). Deep Learning for Fraud Detection in Financial Graphs. ACM Computing Surveys, 55(4), Article 79, 1–26. https://doi.org/10.1145/3468266 DOI: https://doi.org/10.1145/3524496
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Temitayo Oluwaseun Jejeniwa, Titilola Olaide Jejeniwa, Olugbenga Saheed Owolabi
This work is licensed under a Creative Commons Attribution 4.0 International License.
With the licence CC-BY, authors retain the copyright, allowing anyone to download, reuse, re-print, modify, distribute, and/or copy their contribution. The work must be properly attributed to its author.
It is not necessary to ask for further permission from the author or journal board.
This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
