Date of Award

August 2016

Degree Type

Thesis

Degree Name

Master of Science

Department

Engineering

First Advisor

Hamid Seifoddini

Committee Members

Wilkistar A Otieno, Jun Zhang

Keywords

Clustering Algorithm, Factor Analysis, Global Facility Location Factors, Manufacturing Sites

Abstract

The decision making regarding global site selection has been always a challenging and strategic problem. Recently, due to the globalization of the problem many new factors such as political, social, regulatory, government, environmental consideration, etc. gained importance in the decision making process. One of the goals in this thesis is to identify the relevant factors in manufacturing site selection and incorporate them into the data analysis. The collection of a wide range of factors that impact the manufacturing site selection problem at a country level, the quantification of these factors, and incorporation of them into the decision making process needs a quantitative, comprehensive, and flexible approach. In this research hundred countries has been considered for factor analysis and classification. To cluster these countries according to their manufacturing site selection attributes, thirty-four frequently cited attributes are chosen. These factors, also, can be quantified with major economic, business, social, political, and environmental metrics. Factor analysis techniques have used to investigate interrelationships between selected attributes. Our analysis showed that some of these factors can be dropped from our data set. Finally, two types of clustering algorithms, Agglomerative Hierarchical and K-means, are employed to classify countries according to their similarity regrading quantified attributes. We have shown that this approach provides a framework to help the decision making regarding manufacturing facility location selection.

Available for download on Thursday, August 30, 2018

Share

COinS