| Summary: | Today’s supply chain management is facing big challenges; the volume of information flowing into the organizations from various sources is growing. Therefore, an effective solution to provide decision-makers with timely insights and predictive analytics is needed in today’s competitive market.
Data mining, a powerful business intelligence tool, has showed great effects on data analytics and trend prediction in different industries. This report discusses the application of Association Rule Mining Technique (a popular data mining technique) on pattern identification and information extraction in supply chain management. Meanwhile, a web-based application is designed and implemented to find meaningful patterns in large supply chain database as well.
The main content of this report is divided into three parts. Basic supply chain management knowledge and different data mining techniques are introduced in Background Knowledge of the report; this section also explains how data mining techniques solve constrains in supply chain management theoretically.
Application Design, the second part of main content, focuses on Association Rule Mining (ARM) Techniques and detailed algorithms of three important ARM (Apriori, FP Tree and Matrix Apriori) implemented in this application. Pseudo code, example demonstrations and advantages/disadvantages analysis of each technique are included in this section to provide audience a clear understanding.
Application Results, the last part of main content, starts by introducing all the tools and programming languages used to develop web application including Microsoft Visual Studio, ASP.NET framework, C# and HTML. It then demonstrates the detailed structure of this application including designs of graphical user interfaces, functional business process designs and special data representation functionalities.
|
|---|