摘要：Weather index insurance is an innovative tool in risk transfer for disasters induced by natural hazards. This paper proposes a methodology that usesmachine learning algorithms for the identification of extreme flood and drought events aimed at reducing the basis risk connected to this kind ofinsurance mechanism. The model types selected for this study were the neural network and the support vector machine, vastly adopted forclassification problems, which were built exploring thousands of possible configurations based on the combination of different model parameters. Themodels were developed and tested in the Dominican Republic context, based on data from multiple sources covering a time period between 2000 and2019. Using rainfall and soil moisture data, the machine learning algorithms provided a strong improvement when compared to logistic regressionmodels, used as a baseline for both hazards. Furthermore, increasing the amount of information provided during the training of the models proved tobe beneficial to the performances, increasing their classification accuracy and confirming the ability of these algorithms to exploit big data andtheir potential for application within index insurance products.
