Insurers Turn to AI for Weather Risk as Storm Costs Surge
Property and casualty insurers are rapidly integrating artificial intelligence (AI) into their weather risk assessment processes as losses from extreme weather events continue to mount, according to new research from ZestyAI, a climate and property risk analytics provider that uses machine learning to predict weather-related damage.
The survey of 200 senior insurance executives reveals that 25% of firms now use AI models – computer systems that can analyse vast datasets to identify patterns and make predictions – to assess convective storm risks, while 18% deploy the technology for wildfire threat evaluation.
Traditional approaches still dominate the sector, with 54% of insurers relying on actuarial models that use historical data for wildfire assessment. For storm risk, 45% favour stochastic models, which use probability theory to predict future events.
Insurance industry debate over risk assessment techniques
The findings highlight disagreement within the sector about the most effective risk assessment methods. Traditional actuarial approaches are considered most accurate by 27% of respondents, while 26% prefer stochastic modelling. AI and machine learning models are viewed as most reliable by 20% of executives.
“With the growing threat of extreme weather events, we are seeing accelerated rates of adoption of AI-driven models within the insurance industry to assess risk,” says Attila Toth, Founder and Chief Executive Officer of ZestyAI.
The research indicates that adoption by industry peers is the primary factor in selecting new AI risk models, with 45% of respondents ranking this as their top criterion. Price considerations rank third at 37%, while regulatory approval influences 31% of decision-makers.
Risk mitigation strategies
Despite media coverage suggesting widespread policy cancellations, insurers are pursuing multiple approaches to manage climate risks. Only 32% of firms prioritise non-renewals as a strategy. The research shows companies favour property inspections, manual reviews, and adjustments to deductibles and actual cash value roof endorsements.
The survey reveals that 90% of executives want more transparency in predictive models to improve communication with policyholders about risk mitigation measures. This comes as insurers seek to maintain coverage while adapting to increasing weather-related threats.
Storm losses top risk concerns
Insured losses from severe storms in the United States increased from US$30bn in 2022 to US$50bn in 2023, pushing convective storms to the top of risk concerns for 34% of senior managers in actuarial, product management and underwriting roles.
The sector appears convinced of AI's strategic importance, with 73% of executives stating that insurance carriers who adopt the technology will gain competitive advantage. Among firms that have already implemented AI risk models, 81% believe they are better positioned than competitors to handle climate change challenges, compared to 66% of those using traditional models.
“AI has an incredible capacity to transform the insurance industry by enhancing the capability of carriers to protect the assets and wellbeing of policyholders in an increasingly complex world,” says Toth.
Make sure you check out the latest industry news and insights at InsurTech and also sign up to our global conference series - FinTech LIVE 2024 and InsurTech LIVE 2025
InsurTech is a BizClik brand
