Predição de sinistros agrícolas: uma abordagem comparativa utilizando aprendizagem de máquina

Crop insurance has gained greater attention in Brazil since the beginning of the past decade, with the implementation of the Rural Insurance Premium Subvention Program. The present study tested the performance of Machine Learning algorithms for insurers to forecast the occurrence of a claim, using d...

Full description

Bibliographic Details
Authors: Mota, Arthur Lula, Miquelluti, Daniel Lima, Ozaki, Vitor Augusto
Format: article
Status:Published version
Publication Date:2020
Country:Brasil
Institution:Universidade de São Paulo (USP)
Repository:Economia Aplicada
Language:Portuguese
OAI Identifier:oai:revistas.usp.br:article/161194
Online Access:https://www.revistas.usp.br/ecoa/article/view/161194
Access Level:Open access
Keyword:seguro agrícola
sinistro
previsão
machine learning
crop insurance
insurance claim
forecast
Description
Summary:Crop insurance has gained greater attention in Brazil since the beginning of the past decade, with the implementation of the Rural Insurance Premium Subvention Program. The present study tested the performance of Machine Learning algorithms for insurers to forecast the occurrence of a claim, using data from policies and climate databases between the years of 2006 and 2017. The Random Forest, Support Vector Machine and k-Nearest Neighbors algorithms were tested. The second method showed a better predictive performance of claims. However, all methods presented a low predictive capacity for the occurrence of claims.