Federated Learning for Insurance Companies

February 2024

Authors

Panyi Dong
Runhuan Feng, FSA, CERA, PhD
Zhiyu Quan, PhD
Tianyang Wang, ASA, CFA, FRM, PhD

Overview

Federated learning (FL) describes a distributed machine-learning framework enabling multiple devices or organizations to collaborate on a machine-learning model without having to share their raw data with each other or with a central server. One promising application of FL lies in the insurance industry, where each firm harvests a vast amount of client and claims data. There has been little to no previous literature on the applications of FL on insurance data. This paper aims to fill the gap and to offer researchers and practitioners an introduction, the pros and cons of FL, as well as potential use cases.

Report

Federated Learning for Insurance Companies

Podcast

Acknowledgements

The researchers’ deepest gratitude goes to those without whose efforts this project could not have come to fruition: the Project Oversight Group for their diligent work overseeing, reviewing and editing this report for accuracy and relevance.

Project Oversight Group members:
Syed Muhammad Razi Hasnain, ASA, ACIA
Tariq Hussain, FSA, MAAA
Blake A. Hill, FSA, FCIA
Eric Hanania Levy
Costin Oarda
Kevin J. Pledge, FSA, FIA
Tina Yang, FSA, CERA, MAAA
Joy Zhang, FSA, CERA, MAAA

At the Society of Actuaries Research Institute:
Korrel Crawford, Senior Research Administrator
R. Dale Hall, FSA, MAAA, CERA, Managing Director of Research
David Schraub, FSA, CERA, MAAA, AQ, Senior Practice Research Actuary

Questions or Comments?

Give us your feedback! Take a short survey on this report. Take Survey

If you have comments or questions, please send an email to research@soa.org.