Loading...

Using Data Mining In Supply Chain Management (SCM)

Karimi, Hossein | 2010

693 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 40391 (01)
  4. University: Sharif University of Technology
  5. Department: Industrial Engineering
  6. Advisor(s): Salmasi, Naser
  7. Abstract:
  8. Nowadays, finding suppliers of goods and materials is easier than the past, because of developments in communications technology. Therefore, some of supply chains have expanded their relations to global area and select international partners. With an increase in the scope of suppliers available, supplier management sections encounter a large number of suppliers to choose from, and loads of information to process. Therefore proper methods must be adopted in order to evaluate the suppliers. One way is to create credit levels and ranking the suppliers according to past cooperation. Implementation of this method requires the use of tools that provide Comprehensive analysis of the occult rules and patterns within the database. As a result, using data mining techniques can be useful and effective in suppliers' evaluation.In this research work the data mining techniques for identifying the patterns affecting the selection of the suppliers in different conditions have been evaluated. Also, through presenting a classification of suppliers we have tried to evaluate the efficiency of these techniques in determining the properties of credit levels. Also CRISP-DM algorithm has been used for standardizing the process of data mining. In the end of this work, it was found that k-means Clustering technique and the GRI association rules mining technique offer the best performance in most of the relevant areas of this study. ISOICO group’s data and information has been used in this model.

  9. Keywords:
  10. Goods Supply Chain Management ; Data Mining ; Cross-Industry Standard Process for Data Mining (CRISP-DM) ; Suppliers Evaluation ; Suppliers Ranking ; Suppliers Credit Levels

 Digital Object List

 Bookmark

No TOC