Research on insurance decision-making based on the TOPSIS evaluation model and K-means clustering algorithm

Abstract

Increasing losses caused by extreme weather events led to property insurance costs soaring and becoming more challenging to obtain, leaving insurance companies and property owners in a severe crisis. This study aims to address the challenges posed by climate change to the insurance industry and explore the impact of extreme weather events on property insurance. We introduce the TOPSIS evaluation model and K-means clustering algorithm to assess the risk level in different regions and provide the optimal basis for insurance decisions. By analyzing global disaster data and emission indicators, this paper found that some regions face the risk of rejecting underwriting, and used a clustering algorithm. The results show that the increase in property insurance costs aggravates the challenges in the insurance industry, but through the comprehensive assessment model and cluster analysis, we can provide more accurate risk assessment and decision support for insurance companies. By assessing the risk level and effective classification in different regions, it provides insurers with more accurate risk assessment and decision support. The results of this research are of great significance for dealing with the property insurance problems caused by extreme weather events and help the insurance industry better adapt to the challenges of climate change.