Privacy-Enhancing Collaborative Information Sharing through Federated Learning -- A Case of the Insurance Industry

Paper: arXiv 2402.14983

Authors: Panyi Dong, Zhiyu Quan, Brandon Edwards, Shih-han Wang, Runhuan Feng, Tianyang Wang, Patrick Foley, Prashant Shah

Abstract

The report demonstrates the benefits (in terms of improved claims loss modeling) of harnessing the value of Federated Learning (FL) to learn a single model across multiple insurance industry datasets without requiring the datasets themselves to be shared from one company to another. The application of FL addresses two of the most pressing concerns: limited data volume and data variety, which are caused by privacy concerns, the rarity of claim events, the lack of informative rating factors, etc.. During each round of FL, collaborators compute improvements on the model using their local private data, and these insights are combined to update a global model. Such aggregation of insights allows for an increase to the effectiveness in forecasting claims losses compared to models individually trained at each collaborator. Critically, this approach enables machine learning collaboration without the need for raw data to leave the compute infrastructure of each respective data owner. Additionally, the open-source framework, OpenFL, that is used in our experiments is designed so that it can be run using confidential computing as well as with additional algorithmic protections against leakage of information via the shared model updates. In such a way, FL is implemented as a privacy-enhancing collaborative learning technique that addresses the challenges posed by the sensitivity and privacy of data in traditional machine learning solutions. This paper’s application of FL can also be expanded to other areas including fraud detection, catastrophe modeling, etc., that have a similar need to incorporate data privacy into machine learning collaborations. Our framework and empirical results provide a foundation for future collaborations among insurers, regulators, academic researchers, and InsurTech experts.

Complexity vs Empirical Score

• Math Complexity: 3.5/10
• Empirical Rigor: 6.5/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper provides a practical empirical demonstration of Federated Learning using the OpenFL framework applied to insurance claims loss modeling. While mathematical derivations are minimal, the empirical application addresses significant data privacy and volume challenges in quantitative risk modeling.

Research Flowchart

  flowchart TD
    A[Goal: Enhance Insurance Loss Modeling via Privacy-Preserving FL] --> B[Data Inputs: Local Private Insurance Datasets & OpenFL Framework]
    B --> C[Local Training: Collaborators Compute Model Improvements on Private Compute]
    C --> D[Aggregation: Combine Local Insights into a Global Model without Sharing Raw Data]
    D --> E[Confidential Computing & Algorithmic Leakage Protections]
    E --> F[Outcomes: Superior Loss Forecasting & Expandable Privacy Framework]

Cited References (22)

1. Communication-Efficient Learning of Deep Networks from Decentralized Data (2017)
2. A review of applications in federated learning (2020) — link
3. OpenFL: the open federated learning library (2022) — link
4. Loss models: from data to decisions (2012)
5. Social media analytics: Data mining applied to insurance Twitter posts (2012)
6. Machine learning in P&C insurance: A review for pricing and reserving (2021)
7. A machine learning approach for individual claims reserving in insurance (2019)
8. Machine learning approaches for auto insurance big data (2021)

0 of 22 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.