{"title":"Enhancing Supply Chain Transparency and Risk Management Using CNN-LSTM With Transfer Learning","authors":"Yongping Zhang, Achyut Shankar","doi":"10.4018/joeuc.333472","DOIUrl":null,"url":null,"abstract":"Enhancing supply chain transparency and risk management is crucial in modern businesses. The supply chain involves multiple stages and participants, including suppliers, manufacturers, and logistics companies. However, supply chain data is often vast and complex, encompassing various types of information. Effectively analyzing and leveraging this data can help businesses identify potential risks and improvement opportunities. Therefore, a powerful method is needed to process supply chain data and provide accurate predictions and decision support. In this article, the authors approach is based on CNN-LSTM and transfer learning. By comparing with traditional methods and baseline models, this CNN-LSTM model achieved significant improvements in supply chain transparency and risk management. This model accurately predicts potential supply chain risks, providing corresponding decision support. This research is of great significance to enhance the efficiency, reliability, and transparency of the supply chain, offering valuable support for business decision-making.","PeriodicalId":49029,"journal":{"name":"Journal of Organizational and End User Computing","volume":"175 4","pages":"0"},"PeriodicalIF":3.6000,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Organizational and End User Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4018/joeuc.333472","RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
Enhancing supply chain transparency and risk management is crucial in modern businesses. The supply chain involves multiple stages and participants, including suppliers, manufacturers, and logistics companies. However, supply chain data is often vast and complex, encompassing various types of information. Effectively analyzing and leveraging this data can help businesses identify potential risks and improvement opportunities. Therefore, a powerful method is needed to process supply chain data and provide accurate predictions and decision support. In this article, the authors approach is based on CNN-LSTM and transfer learning. By comparing with traditional methods and baseline models, this CNN-LSTM model achieved significant improvements in supply chain transparency and risk management. This model accurately predicts potential supply chain risks, providing corresponding decision support. This research is of great significance to enhance the efficiency, reliability, and transparency of the supply chain, offering valuable support for business decision-making.
期刊介绍:
The Journal of Organizational and End User Computing (JOEUC) provides a forum to information technology educators, researchers, and practitioners to advance the practice and understanding of organizational and end user computing. The journal features a major emphasis on how to increase organizational and end user productivity and performance, and how to achieve organizational strategic and competitive advantage. JOEUC publishes full-length research manuscripts, insightful research and practice notes, and case studies from all areas of organizational and end user computing that are selected after a rigorous blind review by experts in the field.