Segmenting Countries in the Food Packaging Market: A Cluster Analysis Approach

Abstract: The food packaging market has been witnessing substantial growth due to changing consumer lifestyles, urbanization, increased purchasing power, and growing environmental sustainability awareness. This growth presents significant opportunities for companies operating in this market. To effectively capitalize on these opportunities, it is crucial to develop marketing strategies and forecasting analysis that cater to diverse consumer demands across different countries. In this master's thesis, clustering techniques are employed to segment countries in the food packaging market and identify distinct groups of countries based on product packed group, packaging size, and macroeconomic factors. The primary objective of this study is to utilize unsupervised machine learning algorithms, specifically K-means and Hierarchical Clustering, to cluster countries or markets according to packaging product and size for the company in the food packaging industry. The findings indicate that K-Means with six clusters yields a higher Silhouette Score compared to Hierarchical Clustering. Moreover, an analysis of clustering trends from 2015 to 2019 reveals a consistent pattern in country clusters during the period of 2017 to 2019, signifying stability and similarity in country characteristics and packaging volumes. However, variations are observed in the clustering patterns of 2015 and 2016, suggesting distinct country characteristics and package volumes during those years. These findings emphasize the importance of considering temporal trends and dynamics when interpreting clustering results and understanding country characteristics and packaging volumes