Federated Learning for the Design of Parametric Insurance Indices under Heterogeneous Renewable Production Losses

2026-01-17

AI Summary

This study addresses the challenge of balancing privacy preservation and model consistency in the design of parametric insurance indices under heterogeneous renewable energy production losses. To this end, it introduces federated learning to this domain for the first time, proposing a distributed modeling framework based on the Tweedie generalized linear model. Participating entities collaboratively optimize a global deviance objective using algorithms such as FedAvg, FedProx, and FedOpt, without sharing raw data, while accommodating heterogeneous variance structures and link functions. Empirical evaluation on German solar power generation data demonstrates that, under moderate heterogeneity, the proposed approach successfully reproduces the index coefficients obtained from centralized estimation, while significantly enhancing model generalizability and scalability.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

We propose a federated learning framework for the calibration of parametric insurance indices under heterogeneous renewable energy production losses. Producers locally model their losses using Tweedie generalized linear models and private data, while a common index is learned through federated optimization without sharing raw observations. The approach accommodates heterogeneity in variance and link functions and directly minimizes a global deviance objective in a distributed setting. We implement and compare FedAvg, FedProx and FedOpt, and benchmark them against an existing approximation-based aggregation method. An empirical application to solar power production in Germany shows that federated learning recovers comparable index coefficients under moderate heterogeneity, while providing a more general and scalable framework.

Problem

• Federated Learning
• Parametric Insurance
• Renewable Energy
• Heterogeneous Losses
• Tweedie GLM

Innovation

• Federated Learning
• Parametric Insurance
• Tweedie GLM
• Heterogeneous Data
• Distributed Optimization