K. Nguyen, T. Nguyen, Brice M. Nguelifack, C. Jolly
{"title":"Machine Learning Approaches for Predicting Willingness to Pay for Shrimp Insurance in Vietnam","authors":"K. Nguyen, T. Nguyen, Brice M. Nguelifack, C. Jolly","doi":"10.1086/718835","DOIUrl":null,"url":null,"abstract":"Insurance premium prediction is a problem for limited-resource farmers. Econometric methods have generated inaccurate premium forecasts. This article investigates the efficacy of machine learning in predicting insurance premium. Machine learning techniques and survey data on willingness to pay were collected from 534 farmers in Ben Tre, Khanh Hoa, Quang Ninh, and Tra Vinh Provinces, Vietnam. The top-performing models were cubist, random forest, and support vector machines. The cubist model, with the highest R2 and lowest root mean square error, was the most appropriate to forecast premiums. Quantity harvested, total cost, stocking density, and willingness to participate in an insurance program were the top-ranked predictors of premium. Predicted premium payments varied by province. Partial dependence plots showed the economic relationship between predicted premium levels and selected variables. The model results demonstrate that machine learning is useful in forecasting insurance premium and exhibits promise for improving econometric techniques in premium determination.","PeriodicalId":49880,"journal":{"name":"Marine Resource Economics","volume":"37 1","pages":"155 - 182"},"PeriodicalIF":2.0000,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Marine Resource Economics","FirstCategoryId":"96","ListUrlMain":"https://doi.org/10.1086/718835","RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ECONOMICS","Score":null,"Total":0}
引用次数: 1
Abstract
Insurance premium prediction is a problem for limited-resource farmers. Econometric methods have generated inaccurate premium forecasts. This article investigates the efficacy of machine learning in predicting insurance premium. Machine learning techniques and survey data on willingness to pay were collected from 534 farmers in Ben Tre, Khanh Hoa, Quang Ninh, and Tra Vinh Provinces, Vietnam. The top-performing models were cubist, random forest, and support vector machines. The cubist model, with the highest R2 and lowest root mean square error, was the most appropriate to forecast premiums. Quantity harvested, total cost, stocking density, and willingness to participate in an insurance program were the top-ranked predictors of premium. Predicted premium payments varied by province. Partial dependence plots showed the economic relationship between predicted premium levels and selected variables. The model results demonstrate that machine learning is useful in forecasting insurance premium and exhibits promise for improving econometric techniques in premium determination.
期刊介绍:
Marine Resource Economics (MRE) publishes creative and scholarly economic analyses of a range of issues related to natural resource use in the global marine environment. The scope of the journal includes conceptual and empirical investigations aimed at addressing real-world oceans and coastal policy problems. Examples include studies of fisheries, aquaculture, seafood marketing and trade, marine biodiversity, marine and coastal recreation, marine pollution, offshore oil and gas, seabed mining, renewable ocean energy sources, marine transportation, coastal land use and climate adaptation, and management of estuaries and watersheds.