{"title":"大数据驱动的农业供应链风险决策和安全管理","authors":"Guanghe Han, Xin Pan, Xin Zhang","doi":"10.15586/qas.v16i1.1445","DOIUrl":null,"url":null,"abstract":"In the era of digitization, the integration of big data technologies has become instrumental in advancing agri-cultural supply chain management and bolstering risk decision-making processes. Agricultural supply chains, critical to ensuring food security and bolstering rural economies, face vulnerabilities stemming from a myriad of internal and external elements, including natural disasters and market dynamics. Consequently, the urgency to adopt effective risk management strategies is paramount. Contemporary studies have explored the utilization of big data in decision-making processes specific to agricultural supply chain risks, predominantly concentrat-ing on preliminary risk prediction and characterization. Nonetheless, there exists a shortfall in comprehensively analyzing the intricate interplay among risk factors and establishing a holistic risk management decision-making framework based on such analyses. This research addresses these deficiencies through two principal investigative components. First, this research explores the analysis of risk factors and their interrelationships in the agricultural supply chain based on a decision tree algorithm with a transition structure. This algorithm enhances decision-makers’ understanding of risk factors and their interrelationships, and guide the implementation of effective risk mitigation measures and the formulation of contingency plans. Subsequently, the research constructs a corresponding data-driven multi-criteria decision-making method, assisting managers in balancing different risk management strategies in a volatile supply chain environment, considering costs, benefits, and feasibility to formulate the optimal strategy. The innovation of this research lies in the development of a novel risk analysis tool based on the transition decision tree algorithm. This is the first time that such advanced algorithms are applied to agricultural supply chain risk management, filling a gap in the current research. The outcomes of this study not only contribute to enhancing risk management practices within agricultural supply chains but also offer novel insights and methodological tools that are applicable in research and practices across related domains.","PeriodicalId":20738,"journal":{"name":"Quality Assurance and Safety of Crops & Foods","volume":" 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Big data-driven risk decision-making and safety management in agricultural supply chains\",\"authors\":\"Guanghe Han, Xin Pan, Xin Zhang\",\"doi\":\"10.15586/qas.v16i1.1445\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In the era of digitization, the integration of big data technologies has become instrumental in advancing agri-cultural supply chain management and bolstering risk decision-making processes. Agricultural supply chains, critical to ensuring food security and bolstering rural economies, face vulnerabilities stemming from a myriad of internal and external elements, including natural disasters and market dynamics. Consequently, the urgency to adopt effective risk management strategies is paramount. Contemporary studies have explored the utilization of big data in decision-making processes specific to agricultural supply chain risks, predominantly concentrat-ing on preliminary risk prediction and characterization. Nonetheless, there exists a shortfall in comprehensively analyzing the intricate interplay among risk factors and establishing a holistic risk management decision-making framework based on such analyses. This research addresses these deficiencies through two principal investigative components. First, this research explores the analysis of risk factors and their interrelationships in the agricultural supply chain based on a decision tree algorithm with a transition structure. This algorithm enhances decision-makers’ understanding of risk factors and their interrelationships, and guide the implementation of effective risk mitigation measures and the formulation of contingency plans. Subsequently, the research constructs a corresponding data-driven multi-criteria decision-making method, assisting managers in balancing different risk management strategies in a volatile supply chain environment, considering costs, benefits, and feasibility to formulate the optimal strategy. The innovation of this research lies in the development of a novel risk analysis tool based on the transition decision tree algorithm. This is the first time that such advanced algorithms are applied to agricultural supply chain risk management, filling a gap in the current research. The outcomes of this study not only contribute to enhancing risk management practices within agricultural supply chains but also offer novel insights and methodological tools that are applicable in research and practices across related domains.\",\"PeriodicalId\":20738,\"journal\":{\"name\":\"Quality Assurance and Safety of Crops & Foods\",\"volume\":\" 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-03-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Quality Assurance and Safety of Crops & Foods\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.15586/qas.v16i1.1445\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Quality Assurance and Safety of Crops & Foods","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.15586/qas.v16i1.1445","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Big data-driven risk decision-making and safety management in agricultural supply chains
In the era of digitization, the integration of big data technologies has become instrumental in advancing agri-cultural supply chain management and bolstering risk decision-making processes. Agricultural supply chains, critical to ensuring food security and bolstering rural economies, face vulnerabilities stemming from a myriad of internal and external elements, including natural disasters and market dynamics. Consequently, the urgency to adopt effective risk management strategies is paramount. Contemporary studies have explored the utilization of big data in decision-making processes specific to agricultural supply chain risks, predominantly concentrat-ing on preliminary risk prediction and characterization. Nonetheless, there exists a shortfall in comprehensively analyzing the intricate interplay among risk factors and establishing a holistic risk management decision-making framework based on such analyses. This research addresses these deficiencies through two principal investigative components. First, this research explores the analysis of risk factors and their interrelationships in the agricultural supply chain based on a decision tree algorithm with a transition structure. This algorithm enhances decision-makers’ understanding of risk factors and their interrelationships, and guide the implementation of effective risk mitigation measures and the formulation of contingency plans. Subsequently, the research constructs a corresponding data-driven multi-criteria decision-making method, assisting managers in balancing different risk management strategies in a volatile supply chain environment, considering costs, benefits, and feasibility to formulate the optimal strategy. The innovation of this research lies in the development of a novel risk analysis tool based on the transition decision tree algorithm. This is the first time that such advanced algorithms are applied to agricultural supply chain risk management, filling a gap in the current research. The outcomes of this study not only contribute to enhancing risk management practices within agricultural supply chains but also offer novel insights and methodological tools that are applicable in research and practices across related domains.