International Journal of Wireless and Microwave Technologies (IJWMT)
IJWMT Vol. 16, No. 4, 8 Aug. 2026
Cover page and Table of Contents: PDF (size: 1455KB)
A Hybrid Stacked Ensemble Framework for Fraud Detection in Nigerian Financial Ecosystems: Evaluation with Localized Synthetic Data
PDF (1455KB), PP.233-250
Views: 0 Downloads: 0
Author(s)
Jumoke Soyemi
1,2,*
Jamiu R. Olasina
2,3
Index Terms
Fraud detection, Machine Learning, Hybrid Ensemble, Nigerian financial ecosystem
Abstract
Financial fraud presents a major challenge to financial establishments, with Nigerian banks losing over ₦685 million to digital fraud in 2023. Traditional rule-based detection systems have high false-positive rates and limited adaptability; meanwhile, existing machine learning models are generally trained on non-localized datasets that ineffectively represent African fintech ecosystems. This study proposes a Hybrid Stacked Ensemble framework for fraud detection that improves detection accuracy, robustness, and explainability in localized financial environments. The proposed framework combines Random Forest, Gradient Boosting, and Extra Trees as base learners with XGBoost as the meta-classifier and integrates SHAP for model explainability. Performance was evaluated using the Kaggle credit card fraud dataset (284,807 transactions; 0.17% fraud) and a newly curated Nigerian synthetic dataset (150,000 transactions; 1.12% fraud) incorporating localized fraud patterns such as POS, USSD, mobile money, and rural–urban transaction disparities. Class imbalance was addressed using SMOTE oversampling, random undersampling, and cost-sensitive learning. On the Kaggle dataset, the Hybrid Ensemble achieved 99.96% accuracy, 97.14% precision, 79.70% recall, an F1-score of 0.880, and an AUC-ROC of 0.986, outperforming the best individual classifier in recall and AUC-ROC. On the Nigerian dataset, where individual classifiers achieved recall below 3.1%, the proposed framework attained 64.10% recall, an F1-score of 0.460, and an AUC-ROC of 0.866, representing improvements of 106.77% in recall and 488.57% in F1-score over XGBoost. Ablation studies and paired t-tests (p < 0.001) confirmed the effectiveness of the stacking strategy. The study contributes a localized Nigerian fraud dataset, a hybrid stacked ensemble architecture that exploits classifier diversity for improved fraud detection, and an explainable AI framework that enhances transparency, accountability, and regulatory compliance. Deployment as a containerized Streamlit application with JWT authentication demonstrates the framework's practicality as a scalable, explainable, and deployment-ready solution for fraud detection in Nigeria and similar African financial ecosystems.
Cite This Paper
Jumoke Soyemi, Jamiu R. Olasina, "A Hybrid Stacked Ensemble Framework for Fraud Detection in Nigerian Financial Ecosystems: Evaluation with Localized Synthetic Data", International Journal of Wireless and Microwave Technologies(IJWMT), Vol.16, No.4, pp. 233-250, 2026. DOI:10.5815/ijwmt.2026.04.13
Reference
[1]A. Rohilla. Strengthening financial resilience: A holistic approach to combating fraud. Indian Journal of Economics and Finance (IJEF), 4(1):20–31, 2024. https://doi.org/10.54105/ijef.A2566.04010524
[2]S. V. Lieonov, V. V. Bozhenko, and S. V. Mynenko. Promoting public integrity and combating financial crime: Challenges on the pathway to sustainable development, 2023. https://doi.org/10.14254/978-83-963452-7-1/2021
[3]G. G. Castellano, E. Selga, and D. W. Arner. The emergence of financial data governance and the challenge of financial data sovereignty. University of Hong Kong Faculty of Law Research Paper, (2024/20):178–210, 2024. https://doi.org/10.1093/oso/9780197582794.003.0009
[4]A. A. Taha and S. J. Malebary. An intelligent approach to credit card fraud detection using an optimized light gradient boosting machine. IEEE Access, 8:25579–25587, 2020. https://doi.org/10.1109/ACCESS.2020.2971354
[5]S. Gaffaroglu and S. Alp. Detecting frauds in financial statements: A comprehensive literature review between 2019 and 2023 (June). PressAcademia Procedia, 18:47–51, 2024. https://doi.org/10.17261/Pressacademia.2023.1849
[6]P. Hajek, M. Z. Abedin, and U. Sivarajah. Fraud detection in mobile payment systems using an XGBoost-based framework. Information Systems Frontiers, 25(5):1421–1437, 2023. https://doi.org/10.1007/s10796-022-10346-6
[7]D. O. Njoku, V. C. Iwuchukwu, J. E. Jibiri, C. T. Ikwuazom, C. I. Ofoegbu, and F. O. Nwokoma. Machine learning approach for fraud detection system in financial institution: A web-based application. Machine Learning, 20(4):1–12, 2024.
[8]C. D. Ikemefuna, O. Okusi, A. C. Iwuh, and S. Yusuf. Adaptive fraud detection systems: Using ML to identify and respond to evolving financial threats. International Research Journal of Modernization in Engineering, 6:2077–2092, 2024. https://www.doi.org/10.56726/IRJMETS61738
[9]J. Kumar and V. Saxena. Rule-based credit card fraud detection using user’s keystroke behavior. In Soft Computing: Theories and Applications, 469–480, Springer, 2022. https://doi.org/10.1007/978-981-19-0707-4_43
[10]M. Ahmed, K. Ansar, C. B. Muckley, A. Khan, A. Anjum, and M. Talha. A semantic rule-based digital fraud detection. PeerJ Computer Science, 7:e649, 2021. https://doi.org/10.7717/peerj-cs.649
[11]T. Ashfaq, R. Khalid, A. S. Yahaya, S. Aslam, A. T. Azar, S. Alsafari, and I. A. Hameed. A machine learning and blockchain-based efficient fraud detection mechanism. Sensors, 22(19):7162, 2022. https://doi.org/10.3390/s22197162
[12]H. Bodepudi. Credit card fraud detection using unsupervised machine learning algorithms. International Journal of Computer Trends and Technology, 69(1):1–13, 2021. https://doi:10.14445/22312803/IJCTT-V69I8P101
[13]V. N. Dornadula and S. Geetha. Credit card fraud detection using machine learning algorithms. Procedia Computer Science, 165:631–638, 2019. https://doi.org/10.1016/j.procs.2020.01.057
[14]W. M. Ikhsan, E. H. Ednoer, W. S. Kridantika, and A. Firmansyah. Fraud detection automation through data analytics and artificial intelligence. Riset: Jurnal Aplikasi Ekonomi Akuntansi dan Bisnis, 4(2):103–119, 2022. https://doi.org/10.37641/riset.v4i2.166
[15]G. Aguiar, B. Krawczyk, and A. Cano. A survey on learning from imbalanced data streams: Taxonomy, challenges, empirical study, and reproducible experimental framework. Machine Learning, 113(7):4165–4243, 2024. https://doi.org/10.1007/s10994-023-06353-6
[16]V. G. Costa and C. E. Pedreira. Recent advances in decision trees: An updated survey. Artificial Intelligence Review, 56(5):4765–4800, 2023. https://doi.org/10.1007/s10462-022-10275-5
[17]P. Kamuangu. A review on financial fraud detection using AI and machine learning. Journal of Economics, Finance and Accounting Studies, 6(1):67–77, 2024. https://doi.org/10.32996/jefas.2024.6.1.7
[18]Y. Xiao and J. Lian. Credit card fraud detection using SMOTE and ensemble methods. Journal of Physics: Conference Series, 1744(4):042060, 2021.
[19]D. P. Prabha and C. V. Priscilla. Probabilistic XGBoost threshold classification with autoencoder for credit card fraud detection. International Journal on Recent and Innovation Trends in Computing and Communication, 11(8s):528–537, 2023. https://doi.org/10.17762/ijritcc.v11i8s.7234
[20]O. C. Metibemu. Financial risk management in digital-only banks: Addressing fraud and cybersecurity threats in a cashless economy, 2025. SSRN 5166723. https://doi.org/10.9734/ajrcos/2025/v18i3603