•  
  •  
 

Document Type

Original Article

Abstract

Financial fraud detection is difficult because fraudulent transactions are rare, unevenly distributed, and sensitive. This study evaluates a lightweight multilayer perceptron under Federated Averaging (FedAvg), Federated Proximal optimization (FedProx), and Federated Adam (FedAdam), using three seeds and validation-selected decision thresholds. Corrected R4 experiments cover the Credit Card Fraud Detection benchmark, the larger Credit Card Transactions dataset, PaySim as a stand-alone synthetic stress test, and the Bank Account Fraud (BAF) Dataset Suite. On Credit Card, FedProx with 20 clients and alpha = 0.5 achieved F1 = 0.789 +/- 0.010. On Transactions, the best tested federated setting used 10 clients and achieved F1 = 0.347 +/- 0.027, retaining 64.3% of the centralized MLP F1 and 43.1% of the centralized HistGradientBoosting F1. The main-file PaySim run achieved F1 = 0.462 +/- 0.060, but its independent internal split precludes direct numerical comparison with the other datasets. On BAF Base, FedProx achieved F1 = 0.215 +/- 0.015, whereas Variant V collapsed to F1 = 0.039 +/- 0.012. Matched FedProx-FedAvg comparisons did not support general FedProx superiority. Eight-bit upload quantization preserved utility closely while reducing the calculated total payload by approximately 37.5%. These results emphasize threshold behavior, client fragmentation, dataset sensitivity, and payload-level communication rather than a single-model superiority claim.

Receive Date

24 May 2026

Revise Date

25 Aug 2026

Accept Date

06 Sep 2026

Publication Date

10-28-2026

References

[1] Dal Pozzolo A, Caelen O, Johnson RA, Bontempi G. Calibrating probability with undersampling for unbalanced classification. In: 2015 IEEE Symposium Series on Computational Intelligence. Cape Town, South Africa: IEEE; 2015. p. 159—66. https://doi.org/10.1109/SSCI.2015.33.

[2] Saito T, Rehmsmeier M. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS One 2015;10(3): e0118432. https://doi.org/10.1371/journal.pone.0118432.

[3] McMahan HB, Moore E, Ramage D, Hampson S, Aguera y Arcas B. Communication-efficient learning of deep networks from decentralized data. In: Proceedings of the 20th international conference on artificial intelligence and statistics. Fort Lauderdale, Florida, USA: Proceedings of Machine Learning Research (PMLR). PMLR; 2017. p. 1273—82. https://doi.org/ 10.48550/arXiv.1602.05629.

[4] Kairouz P, McMahan HB, Avent B, Bellet A, Bennis M, Bhagoji AN, et al. Advances and open problems in federated learning. Found Trend Mach Learn 2021;14(1―2): 1—210. https://doi.org/10.1561/2200000083.

[5] Abdul Salam M, Fouad KM, Elbably DL, Elsayed SM. Federated learning model for credit card fraud detection with data balancing techniques. Neural Comput Appl 2024; 36:6231—56. https://doi.org/10.1007/s00521-023-09410-2.

[6] Li M, Walsh J. FedGAT-DCNN: advanced credit card fraud detection using federated learning, graph attention networks, and dilated convolutions. Electronics 2024;13(16): 3169. https://doi.org/10.3390/electronics13163169.

[7] Aljunaid SK, Almheiri SJ, Dawood H, Khan MA. Secure and transparent banking: explainable AI-driven federated learning model for financial fraud detection. J Risk Financ Manag 2025;18(4):179. https://doi.org/10.3390/jrfm18040179.

[8] Alhasawi Y, Almtrf AA, Asad M. A federated approach to scalable and trustworthy financial fraud detection. Secur Priv 2025;8(5):e70099. https://doi.org/10.1002/spy2.70099.

[9] Forough J, Momtazi S. Ensemble of deep sequential models for credit card fraud detection. Appl Soft Comput 2021;99: 106883. https://doi.org/10.1016/j.asoc.2020.106883.

[10] Awosika T, Shukla RM, Pranggono B. Transparency and privacy: the role of explainable AI and federated learning in financial fraud detection. IEEE Access 2024;12:64551—60. https://doi.org/10.1109/ACCESS.2024.3394528.

[11] Laridi S, Palmer G, Tam K-MM. Enhanced federated anomaly detection through autoencoders using summary statistics-based thresholding. Sci Rep 2024;14:26704. https:// doi.org/10.1038/s41598-024-76961-2.

[12] Bonawitz K, Ivanov V, Kreuter B, Marcedone A, McMahan HB, Patel S, et al. Practical secure aggregation for privacy-preserving machine learning. In: Proceedings of the 2017 ACM SIGSAC conference on computer and communications security. Dallas, Texas, USA: Association for Computing Machinery (ACM); 2017. p. 1175—91. https:// doi.org/10.1145/3133956.3133982.

[13] Ahmed F, Sanchez D, Haddi Z, Domingo-Ferrer J. MemberShield: a framework for federated learning with membership privacy. Neural Netw 2025;181(art):106768. https:// doi.org/10.1016/j.neunet.2024.106768.

[14] Wu T, Song C, Zeng P. Efficient federated learning on resource-constrained edge devices based on model pruning. Complex Intell Syst 2023;9:6999—7013. https://doi.org/ 10.1007/s40747-023-01120-5.

[15] Min Q, Luo F, Dong W, Gu C, Ding W. Communication-efficient federated learning via personalized filter pruning. Inf Sci 2024;678:121030. https://doi.org/10.1016/j.ins.2024.121030.

[16] Alawadi S, Ait-Mlouk A, Toor S, Hellander A. Toward efficient resource utilization at edge nodes in federated learning. Prog Artif Intell 2024;13:101—17. https://doi.org/ 10.1007/s13748-024-00322-3.

[17] Jiang Y, Wang S, Valls V, Ko BJ, Lee W-H, Leung KK, Tassiulas L. Model pruning enables efficient federated learning on edge devices. IEEE Transact Neural Networks Learn Syst 2023;34(12):10374—86. https://doi.org/10.1109/ TNNLS.2022.3166101.

[18] Pei J, Liu W, Li J, Wang L, Liu C. A Review of Federated Learning Methods in Heterogeneous Scenarios. IEEE Trans Consum Electron 2024;70(3):5983—99. https://doi.org/ 10.1109/TCE.2024.3385440.

[19] Qi P, Chiaro D, Piccialli F. Small models, big impact: a review on the power of lightweight federated learning. Future Gener Comput Syst 2025;162:107484. https://doi.org/10.1016/ j.future.2024.107484.

[20] Jiang Z, Wang S, Valls V, Ko BJ, Lee W-H, Leung KK, et al. Computation and communication efficient federated learning with adaptive pruning. IEEE Trans Mobile Comput 2024;23(3): 2003—18. https://doi.org/10.1109/TMC.2023.3247798.

[21] Zhu Z, Shi Y, Xin G, Peng C, Fan P, Letaief KB. Towards efficient federated learning: layer-wise pruning-quantization scheme and coding design. Entropy 2023;25(8):1205. https://doi.org/10.3390/e25081205.

[22] Cui Y, Jia M, Lin T-Y, Song Y, Belongie S. Class-balanced loss based on effective number of samples. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. Long Beach, California, USA: IEEE/CVF; 2019. p. 9260—9. https://doi.org/10.1109/CVPR.2019.00949.

[23] Li T, Sahu AK, Zaheer M, Sanjabi M, Talwalkar A, Smith V. Federated Optimization in Heterogeneous Networks. Proceedings of Machine Learning and Systems 2020;2:429—50. https://doi.org/10.48550/arXiv.1812.06127.

[24] Reddi SJ, Charles Z, Zaheer M, Garrett Z, Rush K, Konecný J, Kumar S, McMahan HB. Adaptive federated optimization. In: OpenReview.net, International Conference on Learning Representations (ICLR 2021). Virtual Conference; 2021. https://doi.org/10.48550/arXiv.2003.00295.

[25] Abadi M, Chu A, Goodfellow I, McMahan HB, Mironov I, Talwar K, Zhang L. Deep learning with differential privacy. In: Proceedings of the 2016 ACM SIGSAC conference on computer and communications security. Vienna, Austria: Association for Computing Machinery (ACM); 2016. p. 308—18. https://doi.org/10.1145/2976749.2978318.

[26] Gu X, Sabrina F, Fan Z, Sohail S. A review of privacy enhancement methods for federated learning in healthcare systems. Int J Environ Res Publ Health 2023;20(15):6539. https://doi.org/10.3390/ijerph20156539.

[27] Jesus S, Pombal J, Alves D, Cruz A, Saleiro P, Ribeiro RP, Gama J, Bizarro P. Turning the tables: biased, imbalanced, dynamic tabular datasets for ML evaluation. Adv Neural Inf Process Syst 2022;35. https://doi.org/10.52202/068431-2432 (Datasets and Benchmarks Track).

[28] Lopez-Rojas EA, Elmir A, Axelsson S. PaySim: A financial mobile money simulator for fraud detection. In: 28th European modeling and simulation symposium. Larnaca. Cyprus: DIME University of Genoa; 2016. p. 249—55.

Share

COinS