Data Mining: Techniques and Applications in the Manufacturing Industry

Data mining and knowledge discovery in databases are increasingly attracting a significant number of academics, professionals, and the attention of the media. It is regarded by many industrial organisations as an important tool in knowledge discovery with the potential for substantial profits. However, data mining is a relatively new field that has emerged as a result of advancements in many different subjects such as statistics and computing and has only recently began to attract the attention it deserves. As a result, this dissertation provides an overview of this emerging field and demonstrates the potential applications of data mining that can be applied to many domains, in particular to the manufacturing industry. The work starts with distinguishing between the different components of working knowledge. These components are then related to the knowledge discovery process by illustrating the components of this iterative process. Data mining, which is one of the steps in the knowledge discovery process, is then described by discussing the requirements, challenges, techniques, and specific applications in different domains. Finally, two data mining applications in manufacturing will be proposed for future research. The first model tackles the productions strategy decision issues that manufacturers encounter. The production strategies discussed include make-to-order, assemble-to-order, stock-to-order and engineer-to-order strategies. The second model enhances the efficiency of the supply chain by assessing the supplier's risk and facilitating a better outsourcing policy