Review status: this preprint is currently under review for the journal NHESS.
The potential of big data and machine learning for weather index insurance
Luigi Cesarini1,Rui Figueiredo2,Beatrice Monteleone1,and Mario Lloyd Virgilio Martina1Luigi Cesarini et al.Luigi Cesarini1,Rui Figueiredo2,Beatrice Monteleone1,and Mario Lloyd Virgilio Martina1
Received: 23 Jul 2020 – Accepted for review: 07 Aug 2020 – Discussion started: 10 Aug 2020
Abstract. Weather index insurance is an innovative tool in risk transfer for disasters induced by natural hazards. This paper proposes a methodology that uses machine learning algorithms for the identification of extreme flood and drought events aimed at reducing the basis risk connected to this kind of insurance mechanism. The model types selected for this study were the neural network and the support vector machine, vastly adopted for classification problems, which were built exploring thousands of possible configurations based on the combination of different model parameters. The models were developed and tested in the Dominican Republic context, based on data from multiple sources covering a time period between 2000 and 2019. Using rainfall and soil moisture data, the machine learning algorithms provided a strong improvement when compared to logistic regression models, used as a baseline for both hazards. Furthermore, increasing the number of information provided during the training of the models proved to be beneficial to the performances, increasing their classification accuracy and confirming the ability of these algorithms to exploit big data and their potential for application within index insurance products.
Weather index insurance is an innovative program used to manage the risk associated with natural disasters, providing instantaneous financial support to the insured party. This paper proposes a methodology that exploits the power of machine learning and big data to identify extreme events for which a payout from the insurance could be delivered. The improvements achieved using these algorithms are an encouraging step forward in the promotion and implementation of this insurance instrument.
Weather index insurance is an innovative program used to manage the risk associated with natural...