A Comparison Between Statistical and Machine Learning: Methods for Retail Market Segmentation

This study explores the dynamics of consumer behaviour in the retail sector to analyze the varied inclinations, patterns of purchase, and frameworks for making decisions among different groups of people. The study has identified six unique consumer clusters based on a thorough two different methodologies (k-means and Self-Organizing Maps (“SOMs”)). Every cluster exhibits a unique profile that demonstrates the intricacy and subtlety of customer preferences. The results show notable differences in brand loyalty, price sensitivity, and the importance of sustainability, with ramifications for customized marketing strategies. These findings have significant ramifications for retail enterprises. They emphasize how important it is for retailers to tailor their operational and marketing strategies to meet the diverse demands and wants of various consumer segments. It is recommended that retailers make use of these insights to augment customer interaction, refine inventory control, and formulate sophisticated sustainability programs that correspond with consumer preferences. In addition, the study set a direction for more research. Researching how consumer preferences vary over time and evaluating the efficacy of various marketing strategies across various demographic groups, and would be impactful in the realm. A global viewpoint and an enlarged scope would also highlight the impact of culture on buying decisions, offering a thorough understanding of consumers in various economies.