Machine Learning-enhanced approaches to optimization of supply chain management at Nestlé Canada

雀巢加拿大公司正在处理大量来自零售客户的关于产品运输和接收延迟的索赔，这些索赔对公司产生了重大的财务和人力资源影响。因此，需要先进的系统来评估这些索赔和改进程序，以便更好地遵守供应协议。该项目旨在使用创新的数学和机器学习技术来开发适当的决策支持工具。一个工具将对声明进行分类，以提高对不合规原因的理解，而另一个工具将帮助管理清单，以实现改进的合规。这项工作将由三位在供应链管理、先进数据分析方法和业务流程优化方面具有专长的教授监督。研究团队包括一名博士后，一名硕士论文学生和四名硕士非论文学生，他们将与行业代表一起应用他们的研究成果和方法。预期的结果包括在加拿大的一个非常大的业务运营中更有效的供应链流程，这将提高其竞争力和财务回报。

Nestlé Canada is handling very large numbers of claims from their retail customers for delays in shipping and receiving of products, and these claims have substantial financial and human resource impacts on the company. Advanced systems are therefore desired for evaluating these claims and for improving processes to better comply with supply agreements. This project aims to use innovative mathematical and machine learning techniques to develop appropriate decision support tools. One tool will categorise claims to improve understanding of the reasons for noncompliance, while the other tool will help manage inventory to enable improved compliance. The work will be supervised by three professors with expertise in supply chain management, advanced methods in data analysis, and business process optimization. The research team includes one postdoctoral fellow, one Master's thesis student and four Master's non-thesis students who will work with industry representatives to apply results obtained and methods developed from their research. The expected outcomes include more efficient supply chain processes at a very large business operation in Canada, which improve its competitiveness and financial returns.