A Machine Learning Framework for Climate-Resilient Insurance and Real Estate Decisions

TL;DR

This paper introduces integrated machine learning models to assess climate risks in insurance and real estate, providing decision-making tools that improve resilience and sustainability amid increasing weather-related threats.

Contribution

It presents the SSC-Insurance Model combining SMOTE, SVM, and C-D-C algorithms, and the TOA-Preservation Model using TOPSIS-ORM and AHP, for climate risk evaluation and protection prioritization.

Findings

Achieved 88.3% accuracy in Zhejiang and 79.6% in Ireland.

Identified a 43% weather increase as a critical threshold for insurance viability.

Case study showed a 65.32% insurability probability and a protection score of 0.512.

Abstract

Extreme weather events increasingly threaten the insurance and real estate industries, creating conflicts between profitability and homeowner burdens. To address this, we propose the SSC-Insurance Model, which integrates SMOTE, SVM, and C-D-C algorithms to evaluate weather impacts on policies and investments. Our model achieves 88.3% accuracy in Zhejiang and 79.6% in Ireland, identifying a critical threshold (43% weather increase) for insurance viability. Additionally, we develop the TOA-Preservation Model using TOPSIS-ORM and AHP to prioritize building protection, with cultural value scoring highest (weight: 0.3383). Case studies on Nanxun Ancient Town show a 65.32% insurability probability and a protection score of 0.512. This work provides actionable tools for insurers, developers, and policymakers to manage climate risks sustainably.