Privacy-Preserving Federated Risk Scoring for Auto Insurers
Keywords:
Federated Learning in Insurance, Privacy-Preserving Risk Prediction, Secure Multi-Party Computation, Cross-Insurer Collaboration, Auto Insurance Risk Modeling, Regulatory-Compliant Data Analytics, GDPR and CCPA Compliance, Distributed Machine Learning, Client Data Privacy Protection, Federated Prediction Frameworks, Imbalanced Insurance Data, Small and Mid-Sized Insurer Analytics, Pre-Binding Risk Assessment, Premium Pricing Optimization, Cross-Institutional Model Training, Privacy-Aware Predictive Modeling, Decentralized Data Analytics, Collaborative Insurance Intelligence, Secure Federated Architectures, Real-World Federated Learning Deployment.Abstract
Insurance companies often face barriers to sharing data across institutions due to regulatory requirements or privacy concerns. Consequently, client data may be imbalanced or limited, negatively impacting prediction model performance. An innovative risk prediction framework is proposed leveraging Federated Learning (FL) and collaboration between insurers while maintaining data privacy through secure multi-party computation. Experiments demonstrate the approach's effectiveness for prediction tasks with data from different insurers while addressing privacy as a critical concern in a real-world setting.
Collaborating across insurers to improve prediction capabilities and foster a more competitive environment is particularly important for small- or mid-sized auto insurance organizations. Insurers need to know in advance the likelihood of a client suffering an accident in order to set an accurate premium. Setting a value below the acceptable level without sufficient client knowledge may lead to subsequent losses; on the other hand, if the value is too high, the client may seek a cheaper option with another insurer. Thus, prediction tasks should be pursued prior to opening for new business, as the distribution of variables may change. However, data sharing across institutions should not be allowed due to the regulatory requirements (e.g. GPDR or CCPA).
In light of the above, a FL framework is proposed to tackle an auto insurance risk prediction task in which the data are isolated in distinct clients. Importantly, no raw data are shared across participants, and the FL settings are conducted without preserving the trained models. Nevertheless, the framework still encompasses a unity in the business aspect of prediction tasks while ensuring the required privacy.
References
1. Aledhari, M., Razzak, R., Parizi, R. M., & Saeed, F. (2021). Federated learning: A survey on enabling technologies, protocols, and applications. IEEE Access, 9, 140699–140725.
2. Fereidooni, H., Marchal, S., Miettinen, M., Mirhoseini, A., Mollering, H., Nguyen, T. D., Rieger, P., Sadeghi, A. R., Schneider, T., Yalame, H., & Zeitouni, S. (2021). SAFELearn: Secure aggregation for private federated learning. Proceedings of the 2021 IEEE Security and Privacy Workshops, 56–62.
3. Yandamuri, U. S., Loganathan, R., Davuluri, P. S. L. N., Rani, P. R. S., Kolla, S. H., & Nagubandi, A. R. (2026). Adaptive Intelligence Networks for Humancentered Enterprise Automation and Governance. In 2026 Third International Conference on Innovations in Cybersecurity and Data Science (ICICDS) (pp. 678–683). IEEE. 2026 Third International Conference on Innovations in Cybersecurity and Data Science (ICICDS). https://doi.org/10.1109/icicds70526.2026.11604640
4. Jeon, B., Ferdous, S. M., Rahman, M. R., & Walid, A. (2021). Privacy-preserving decentralized aggregation for federated learning. IEEE INFOCOM 2021 Conference on Computer Communications Workshops, 1–6.
5. Kairouz, P., McMahan, H. B., Avent, B., Bellet, A., Bennis, M., Bhagoji, A. N., Bonawitz, K., Charles, Z., Cormode, G., Cummings, R., D’Oliveira, R. G. L., Eichner, H., El Rouayheb, S., Evans, D., Gardner, M. J., Garrett, Z., Gascón, A., Ghazi, B., Gibbons, P. B., ... Zhao, S. (2021). Advances and open problems in federated learning. Foundations and Trends in Machine Learning, 14(1–2), 1–210.
6. Mangalampalli, B. M., Peddi, R. K., Kolla, S. K., Reddy, V. A. R., Mangala, N., & Seenu, A. (2026, June). Explainable Clinical Graph Intelligence Framework for Longitudinal Risk Modeling and Care Pathway Optimization. In 2026 Third International Conference on Innovations in Cybersecurity and Data Science (ICICDS) (pp. 1-6). IEEE.
7. Zhang, K., Song, X., Zhang, C., & Yu, S. (2022). Challenges and future directions of secure federated learning: A survey. Frontiers of Computer Science, 16, Article 165817.
8. Zheng, Y., Lai, S., Liu, Y., Yuan, X., Yi, X., & Wang, C. (2023). Aggregation service for federated learning: An efficient, secure, and more resilient realization. IEEE Transactions on Dependable and Secure Computing, 20(2), 988–1001.
9. Liu, Z., Lin, H., & Liu, Y. (2023). Long-term privacy-preserving aggregation with user-dynamics for federated learning. IEEE Transactions on Information Forensics and Security, 18, 2398–2412.
10. Banoth, S., Santoshi Kumari, M., Lalitha, P., Deepthi, P., Kumar Peddi, R., & Kavitha, P. (2026). An Efficient Hybrid K-Means and Random Forest-Based Approach for Cloud Malware Detection and Privacy Protection. In 2026 6th International Conference on Intelligent Technologies (CONIT) (pp. 1–6). IEEE. 2026 6th International Conference on Intelligent Technologies (CONIT). https://doi.org/10.1109/conit69683.2026.11621822
11. Eltaras, T. A., Sabry, F., Labda, W., Alzoubi, K., & Malluhi, Q. (2023). Efficient verifiable protocol for privacy-preserving aggregation in federated learning. IEEE Transactions on Information Forensics and Security, 18, 2977–2990.
12. Zhang, Z., Li, J., Yu, S., & Makaya, C. (2023). SAFELearning: Secure aggregation in federated learning with backdoor detectability. IEEE Transactions on Information Forensics and Security, 18, 3289–3304.
13. Li, K. H., Buarque de Gusmão, P. P., Beutel, D. J., & Lane, N. D. (2022). Secure aggregation for federated learning in Flower. arXiv preprint arXiv:2205.06117.
14. Mahadevan, S. (2026). Governed Serverless Automation Ecosystem for AI-Driven Enterprise Integration and Sustainable Cloud Operations. International Journal of Computer Information Systems and Industrial Management Applications, 18(16s), 1561-1570.
15. Sun, L., Tan, Y., & Wang, J. (2022). A survey on federated learning systems: Vision, applications, and future directions. IEEE Transactions on Artificial Intelligence, 3(5), 789–807.
16. Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2022). Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology, 13(2), Article 12.
17. Meng, S., Gao, Y., & Huang, Y. (2022). Actuarial intelligence in auto insurance: Claim frequency modeling with driving behavior features and improved boosted trees. Insurance: Mathematics and Economics, 106, 115–127.
18. Rafi, T. H., Noor, F. A., Hussain, T., & Chae, D.-K. (2023). Fairness and privacy preserving in federated learning: A survey. Information Fusion, 102198.
19. Piyush Kumar Pareek. (2026). Human-Centric Machine Learning Frameworks for Scalable Software Quality Prediction. Journal of Intelligent Decision Making and Information Science, 3(5s), 1525–1543. https://doi.org/10.59543/jidmis.v3.1284
20. Li, H.-J., Li, J.-Q., & colleagues. (2023). Driving risk prevention in usage-based insurance services based on interpretable machine learning and telematics data. Decision Support Systems, 172, 113985.
21. Strada, S., Costantini, E., Formentin, S., & Savaresi, S. M. (2025). Machine learning based car accident risk prediction for usage-based insurance. Intelligent Data Analysis, 29(1), 1–20.
22. Yao, Y., Sun, Z., & Zhang, Y. (2021). A survey on security and privacy of federated learning. Future Generation Computer Systems, 115, 619–640.
23. Mothukuri, V., Parizi, R. M., Pouriyeh, S., Huang, Y., Dehghantanha, A., & Srivastava, G. (2021). A survey on security and privacy of federated learning. Future Generation Computer Systems, 115, 619–640.
24. Vakkalagadda, T., & Rajamanickam, V. (2026). Agentic AI Architectures for Next-Generation Investment Advisory and Portfolio Intelligence. International Journal of Computer Information Systems and Industrial Management Applications, 18(9s), 1206-1219.
25. Zhang, X., Li, Y., Cui, Z., Cui, Y., & Zhang, J. (2022). A survey on federated learning: Challenges and applications. International Journal of Machine Learning and Cybernetics, 13, 1–18.
26. Saha, S., Hota, A., Chattopadhyay, A. K., Nag, A., & Nandi, S. (2024). A multifaceted survey on privacy preservation of federated learning: Progress, challenges, and opportunities. Artificial Intelligence Review, 57, Article 184.
27. Zhao, J., Bagchi, S., Avestimehr, S., Chan, K., Chaterji, S., Dimitriadis, D., Li, J., Li, N., Nourian, A., & Roth, H. (2025). The federation strikes back: A survey of federated learning privacy attacks, defenses, applications, and policy landscape. ACM Computing Surveys, 57(9), Article 230.
28. Loganathan, R. (2026). SaaS Entitlement Governance: A Reproducible Model for Detecting and Reclaiming Over-Provisioned Access at Enterprise Scale. Journal of Intelligent Decision Making and Information Science, 3(7s), 2519-2530.
29. Li, J., Liu, Z., & Wang, H. (2023). Privacy-preserving federated learning via functional encryption, revisited. IEEE Transactions on Information Forensics and Security, 18, 1855–1869.
30. Xie, H., Wang, Y., Ding, Y., & Yang, C. (2023). Verifiable federated learning with privacy-preserving data aggregation for consumer electronics. IEEE Transactions on Consumer Electronics.
31. Bhavani, B. D., SR, S., Loganathan, R., & Nagaraj, S. (2026, April). Evolutionary Gravitational Neocognitron Neural Network, Snow Leopard Optimization and Deep Graph Reinforcement Learning for Routing Protocol in WSN. In 2026 2nd International Conference on Intelligent Systems and Computational Networks (ICISCN) (pp. 1-8). IEEE.
32. Hahn, C., Kim, H., Kim, M., & Hur, J. (2023). VerSA: Verifiable secure aggregation for cross-device federated learning. IEEE Transactions on Dependable and Secure Computing, 20(1), 36–52.
33. Davuluri, P. S. L. (2023). AI-Augmented Sanctions Screening: Enhancing Accuracy and Latency in Real Time Compliance Systems. AI-Augmented Sanctions Screening: Enhancing Accuracy and Latency in Real Time Compliance Systems (December 15, 2023).
34. Jiang, Y., Ma, B., Wang, X., Yu, G., Sun, C., & Liu, R. P. (2023). A secure aggregation for federated learning on long-tailed data. IEEE Internet of Things Journal.
35. Zhao, Y., Chen, J., Wu, D., Teng, J., & Yu, S. (2022). Multi-task network for privacy-preserving federated learning. IEEE Transactions on Dependable and Secure Computing.
36. Ganesh, S. K., Subbareddy, K., Gopi, A., Davuluri, P. N., Mannar, B. R., & Karnawat, A. T. (2026, June). Fraudulent Credit Card Transaction Detection Using a Hybrid Ensemble-Anomaly Detection Framework. In 2026 6th International Conference on Intelligent Technologies (CONIT) (pp. 1-6). IEEE.
37. Yang, W., Zhang, Y., Ye, K., Li, L., & Xu, W. (2021). FFD: A federated learning system for fraud detection. IEEE Transactions on Dependable and Secure Computing.
38. Ubale, A. (2025). Privacy-preserving federated learning frameworks for telematics data in auto insurance analytics. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 6(4), 41–48.
39. Piyush Kumar Pareek. (2026). Self-Evolving Analytics Pipelines for Reliable AI-Augmented Software Systems. Journal of Intelligent Decision Making and Information Science, 3(5s), 1558–1578. https://doi.org/10.59543/jidmis.v3.1286
40. Davis, J., Smith, J., & Williams, R. (2026). Design of privacy-preserving federated learning models for auto insurance telematics. ScienceOpen Preprints.
41. Anonymous. (2026). Secure aggregation with verifiability and robustness for privacy-preserving federated learning. Knowledge-Based Systems.
Additional Files
Published
Data Availability Statement
None
Issue
Section
License
Copyright (c) 2026 Emma Richardson (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). Authors retain full copyright of their published work. Under this license, others are free to share, copy, distribute, transmit, remix, transform, and build upon the published work for any purpose, including commercial use, provided that appropriate credit is given to the original authors, a link to the license is provided, and any changes made are clearly indicated. No additional restrictions may be applied that limit others from doing anything the license permits. All published articles are freely and permanently accessible online to readers worldwide without any subscription or access fees.
License URL: https://creativecommons.org/licenses/by/4.0/
