Risk management for cyber insurance: a survey for data-driven approaches with the use of AI

This article provides a systematic survey of data-driven approaches to cyber insurance risk management. It reviews the literature on cybersecurity data sources, data collection practices, risk calculation methods and insurance pricing strategies. Traditional actuarial approaches are examined alongside emerging AI-enabled methods, including supervised learning, predictive analytics and simulation-based techniques. The article also identifies key challenges related to data quality, standardisation, data sharing and model interpretability and outlines future research directions for more automated, evidence-based and AI-supported cyber insurance underwriting and pricing.

This work has received funding from the European Union’s Digital Europe research and innovation programme under Grant Agreement No. 101128013 (ERMIS).