Machine learning-based climate risk sharing for an insured loan in the tourism industry

Higher risks for commercial banks correspond to lower probability of access to fnancing transactions. Climate change risk strongly impacts bank loan supply. In particular, in the tourism industry, it is noteworthy that lenders charge higher interest rates for mortgages that face a greater risk of rising sea levels. As loans are one of the most important businesses for commercial banks, innovative strategies can lead to the design of a composite bank loan supply for building resilience, especially against physical climate risk. In this work, we propose a new tool, which is an insured loan relying on a climate change risksharing mechanism, where we develop a bioclimatic composite indicator based on machine learning naïve technique.