Federated Learning for Shariʿah-Compliant Credit Scoring in Islamic Banks: Preserving Data Privacy and Eliminating Riba-Related Features
DOI:
https://doi.org/10.61455/deujis.v4i01.616Keywords:
federated learning, shariʿah-compliant credit scoring, riba elimination, islamic banking, differential privacyAbstract
Objective: The rapid expansion of Islamic banking across Africa, Southeast Asia, and the GCC region requires credit assessment frameworks that are privacy-preserving, data-efficient, and strictly Shariʿah-compliant. This study proposes FedIslami, a novel federated learning framework designed to train credit-scoring models collaboratively across distributed Islamic bank branches without transmitting sensitive raw client records. Theoretical framework: The study is theoretically grounded in the Islamic principle of Amānah (trusteeship of client data) and Maqāsid al-Shariʿah objectives, establishing an ethical foundation for data privacy, algorithmic justice, and religious compliance within modern financial engineering. Literature Review: Existing literature highlights that conventional machine learning models violate data trusteeship through centralised data aggregation and systematically incorporate interest-rate exposure metrics, debt-service-coverage ratios, and other Ribā-indexed features that are impermissible under Shariʿah law. Method: FedIslami systematically excises fourteen identified Ribā-contaminated features, replacing them with Shariʿah-permissible analogues. Utilising FedAvg with differential privacy (DP-FedAvg) and homomorphic encryption secure aggregation, the model was validated on 214,736 anonymised financing records (2019–2024) across nine Islamic banks in Nigeria, Malaysia, UAE, and Bangladesh. Results: FedIslami achieved outstanding predictive accuracy with an AUC of 0.894, a Gini coefficient of 0.788, and a Kolmogorov-Smirnov statistic of 0.581, significantly outperforming non-federated centralised baselines (0.871) and conventional federated models retaining Ribā features (0.842). The audit confirmed full compliance with AAOIFI Governance Standard No. 7 and IFSB-16. Implications: This research demonstrates that privacy-preserving federated learning effectively bridges performance gaps between modern Islamic and conventional credit-scoring systems while simultaneously reinforcing institutional ethical and religious data-governance obligations. Novelty: FedIslami introduces the first dual-layer privacy-preserving federated learning architecture that simultaneously addresses client privacy and algorithmic Shariʿah compliance through systemic Ribā feature elimination and Maqāsid-aligned variable substitution.
References
S. Pokhrel and R. Chhetri, “A Literature Review on Impact of COVID-19 Pandemic on Teaching and Learning,” High. Educ. Futur., vol. 8, no. 1, pp. 133–141, 2021, https://doi.org/10.1177/2347631120983481.
H. He, Z. Wang, H. Jain, C. Jiang, S. Yang, and J. Wang, “Capturing Invariance on Multi-Party Data for Decentralised Credit Scoring,” ACM Trans. Manag. Inf. Syst., vol. 16, no. 4, 2025, https://doi.org/10.1145/3728366.
H. Tang, “How to Promote Data Sharing of Financial Service Providers Based on Federated Learning Technology,” Inf. Resour. Manag. J., vol. 37, no. 1, 2024, https://doi.org/10.4018/IRMJ.358747.
R. Shokri, M. Stronati, C. Song, and V. Shmatikov, “Membership Inference Attacks Against Machine Learning Models,” Proc. - IEEE Symp. Secur. Priv., pp. 3–18, 2017, https://doi.org/10.1109/SP.2017.41.
F. O. F. Arsénio, A. Raimundo, and J. P. C. B. B. Pavia, “Anticipating Financial Risk: Machine Learning for Debt Management in Telecommunications,” IEEE Access, vol. 14, pp. 29523–29538, 2026, https://doi.org/10.1109/ACCESS.2026.3665976.
T. D. Warninda, I. A. Ekaputra, and R. Rokhim, “Do Mudarabah and Musharakah financing impact Islamic Bank credit risk differently?” Res. Int. Bus. Financ., vol. 49, pp. 166–175, 2019, https://doi.org/10.1016/j.ribaf.2019.03.002.
A. Oualid, Y. Qasmaoui, Y. Balouki, B. Itri, and L. Moumoun, “Advancing Credit Risk Management in Open Banking with Enhanced Federated Averaging Algorithm,” Eng. Technol. Appl. Sci. Res., vol. 15, no. 3, pp. 22573–22579, 2025, https://doi.org/10.48084/etasr.10266.
M. Sivasundaram, M. Selvam, P. Venkatachalam, and R. T. Rajasekaran, “Adaptive secure federated cloud framework for high-accuracy fraud detection in financial systems,” Automatika, vol. 67, no. 1, pp. 452–466, 2026, https://doi.org/10.1080/00051144.2026.2668191.
S. Hua et al., “An FTwNB Shield: A Credit Risk Assessment Model for Data Uncertainty and Privacy Protection,” Mathematics, vol. 12, no. 11, 2024, https://doi.org/10.3390/math12111695.
Z. Xu, J. Cheng, L. Cheng, X. Xu, and M. Bilal, “MSEs Credit Risk Assessment Model Based on Federated Learning and Feature Selection,” Comput. Mater. Contin., vol. 75, no. 3, pp. 5573–5595, 2023, https://doi.org/10.32604/cmc.2023.037287.
A. J. Almalki, “Unsupervised Learning With Hybrid Models for Detecting Electricity Theft in Smart Grids,” IEEE Access, vol. 12, pp. 187027–187040, 2024, https://doi.org/10.1109/ACCESS.2024.3498733.
K. Yuan and J. Wu, “FedVI: Financial Cross-Domain Federated Learning with Scarce Overlapping Samples via Visual Representation of Heterogeneous Tabular Data and Meta-Optimization,” Entropy, vol. 28, no. 6, 2026, https://doi.org/10.3390/e28060637.
F. Yang, M. Z. Abedin, and P. Hajek, “An explainable federated learning and blockchain-based secure credit modelling method,” Eur. J. Oper. Res., vol. 317, no. 2, pp. 449–467, 2024, https://doi.org/10.1016/j.ejor.2023.08.040.
K. S. Hebbar, V. Sharma, and J. A. Maheshkar, “Edge-AI microservice orchestration for private, real-time generative FinTech applications,” Futur. Technol., vol. 5, no. 2, pp. 13–24, 2026, https://doi.org/10.55670/fpll.futech.5.2.2.
S. M. Al Mujahidin, M. A. Q. Riyadi, A. M. Dewi, and M. Kamal, “Robust Aggregation Strategies in Federated Learning for Credit Risk Assessment,” J. RESTI, vol. 9, no. 6, pp. 1366–1374, 2025, https://doi.org/10.29207/resti.v9i6.7133.
X. Ning et al., “A corporate credit evaluation method considering strong feature privacy with non-private label: A vertical heterogeneous feature fusion approach,” Intell. Syst. with Appl., vol. 28, 2025, https://doi.org/10.1016/j.iswa.2025.200603.
Z. Jovanovic, Z. Hou, K. Biswas, and V. Muthukkumarasamy, “Robust integration of blockchain and explainable federated learning for automated credit scoring,” Comput. Networks, vol. 243, 2024, https://doi.org/10.1016/j.comnet.2024.110303.
A. Aldrees, S. Shahab, A. K. Dutta, W. Ahmad, and M. Anjum, “Behavioural Patterns in Micro-lending: Enhancing Credit Risk Assessment with Collaborative Filtering and Federated Learning,” Int. J. Comput. Intell. Syst., vol. 18, no. 1, 2025, https://doi.org/10.1007/s44196-025-00776-w.
J. Nalavade, R. S. Sajjan, K. Bhosle, A. Buchade, M. N. Vharkate, and C. H. Nemade, “Regulatory-Driven Federated Learning: A Multi-Objective Approach to Compliance and Ethical AI in Financial Systems,” J. Intell. Decis. Mak. Inf. Sci., vol. 3, no. 8S, pp. 91–104, 2026, https://doi.org/10.59543/jidmis.v3.1971.
Y. R. Wang and Y. C. Tsai, “The Protection of Data Sharing for Privacy in Financial Vision,” Appl. Sci., vol. 12, no. 15, 2022, https://doi.org/10.3390/app12157408.
Q. Yang, Y. Liu, T. Chen, and Y. Tong, “Federated machine learning: Concept and applications,” ACM Trans. Intell. Syst. Technol., vol. 10, no. 2, pp. 1–19, 2019, https://doi.org/10.1145/3298981.
M. K. Hassan and S. Aliyu, “A contemporary survey of Islamic banking literature,” J. Financ. Stab., vol. 34, pp. 12–43, 2018, https://doi.org/10.1016/j.jfs.2017.11.006.
K. Bonawitz et al., “Practical secure aggregation for privacy-preserving machine learning,” in Proceedings of the ACM Conference on Computer and Communications Security, 2017, pp. 1175–1191. https://doi.org/10.1145/3133956.3133982.
J. Wu, H. Xu, T. Zhang, R. Xu, H. Wu, and Z. Huang, “IVA-FL: An information-value-aware federated learning framework for Privacy-Preserving Financial Data Risk Management,” PLoS One, vol. 21, no. 3 March, 2026, https://doi.org/10.1371/journal.pone.0344251.
I. A. Abed, N. Hussin, M. A. Ali, H. Haddad, M. Shehadeh, and E. F. Hasan, “Creative Accounting Determinants and Financial Reporting Quality: Systematic Literature Review,” Risks, vol. 10, no. 4, p. 76, 2022, https://doi.org/10.3390/risks10040076.
Y. Zheng, “Bank data protection and fraud identification based on improved adaptive federated learning and WGAN,” Sci. Rep., vol. 15, no. 1, 2025, https://doi.org/10.1038/s41598-025-06807-y.
S. K. Aljunaid, S. J. Almheiri, H. Dawood, and M. A. Khan, “Secure and Transparent Banking: Explainable AI-Driven Federated Learning Model for Financial Fraud Detection,” J. Risk Financ. Manag., vol. 18, no. 4, 2025, https://doi.org/10.3390/jrfm18040179.
W. Luo, Q. Fang, and W. Kang, “Symmetry-Preserving Federated Learning with Blockchain-Based Incentive Mechanisms for Decentralised AI Networks,” Symmetry (Basel), vol. 17, no. 11, 2025, https://doi.org/10.3390/sym17111977.
S. Wang, “Federated Semantic Web Framework for Enhanced Financial Risk Control and Data Analysis,” Int. J. Semant. Web Inf. Syst., vol. 21, no. 1, 2025, https://doi.org/10.4018/IJSWIS.367469.
T. Selvamani, P. Arjunan, and E. Poovammal, “Intelligent Mortgage Optimisation: Leveraging AI for Personalised Lending and Risk Assessment,” Int. J. Basic Appl. Sci., vol. 14, no. 2, pp. 113–118, 2025, https://doi.org/10.14419/psrwrt75.
V. S. Naresh and D. Ayyappa, “Privacy-preserving federated credit risk models: evaluating differential privacy and homomorphic encryption techniques,” Sci. Rep., vol. 16, no. 1, 2026, https://doi.org/10.1038/s41598-025-34536-9.
H. Fan and M. Alenezi, “Research on the Implementation of Financial Risk Control Models and Algorithms Based on Machine Learning,” Int. J. e-Collaboration, vol. 20, no. 1, 2024, https://doi.org/10.4018/IJeC.351248.
Q. Wu, Y. Lei, and Z. Chen, “FedResAttNet: a federated deep residual attention network for cross-institutional loan default prediction,” PeerJ Comput. Sci., vol. 12, 2026, https://doi.org/10.7717/peerj-cs.3972.
A. Imteaj and M. H. Amini, “Leveraging asynchronous federated learning to predict customers' financial distress,” Intell. Syst. with Appl., vol. 14, 2022, https://doi.org/10.1016/j.iswa.2022.200064.
Q. Wu, M. Shahbaz, S. Makhmudov, W. Huang, Z. Liu, and Y. Lei, “A Cross-Institutional Financial Fraud Collaborative Detection Algorithm Based on FedGAT Federated Graph Attention Network,” Symmetry (Basel), vol. 18, no. 3, 2026, https://doi.org/10.3390/sym18030546.
P. Ramachandra and S. Vaithiyanathan, “Fed-DPSDG-WGAN: Differentially Private Synthetic Data Generation for Loan Default Prediction via Federated Wasserstein GAN,” IEEE Access, vol. 13, pp. 52069–52084, 2025, https://doi.org/10.1109/ACCESS.2025.3552487.
R. Li et al., “A dynamic receptive field and improved feature fusion approach for federated learning in financial credit risk assessment,” Sci. Rep., vol. 14, no. 1, 2024, https://doi.org/10.1038/s41598-024-77310-z.
B. Liu, L. Chen, H. Jiang, and R. Ma, “A Starfish Optimisation Algorithm-Based Federated Learning Approach for Financial Risk Prediction in Manufacturing Enterprises,” Int. J. Adv. Comput. Sci. Appl., vol. 16, no. 9, pp. 175–183, 2025, https://doi.org/10.14569/IJACSA.2025.0160918.
A. M. Awadelkarim, “Federated and Interpretable AI Framework for Secure and Transparent Loan Default Prediction in Financial Institutions,” Math. Comput. Appl., vol. 31, no. 2, 2026, https://doi.org/10.3390/mca31020056.
M. Yuxin and W. Honglin, “Federated Learning Based on Data Divergence and Differential Privacy in Financial Risk Control Research,” Comput. Mater. Contin., vol. 75, no. 1, pp. 863–878, 2023, https://doi.org/10.32604/cmc.2023.034879.
B. Li, “Multimodal federated learning for detecting financial anomalies in enterprise cloud systems,” Int. J. Inf. Commun. Technol., vol. 27, no. 34, pp. 74–90, 2026, https://doi.org/10.1504/IJICT.2026.10077361.
C. Du, J. Xiao, and W. Guo, “Bandwidth-constrained client selection and scheduling for federated learning over SD-WAN,” IET Commun., vol. 16, no. 2, pp. 187–194, 2022, https://doi.org/10.1049/cmu2.12333.
