Enhancing Wholesale Management Through Machine Learning-Based Customer Behavior Analysis

Abstract

This study concentrates on the analysis of wholesale customer data to enhance the understanding of consumer behavior and expenditure trends. The dataset has information about how much people spend each year on Fresh, Milk, Grocery, Frozen, Detergents_Paper, and Delicassen, as well as what kind of client they are (Retail or Horeca) and where they live. A Random Forest Classifier was used with machine learning (ML) to forecast the types of clients, and it worked quite well. K-Means clustering was then used to split customers into categories depending on how much they spent. The analysis gives firms information about how to group and classify customers, which helps them make better decisions and adjust their marketing tactics. This study demonstrates the efficacy of integrating classification and clustering approaches for substantive customer analysis by tackling problems such as high-dimensional data. These findings underscore the potential of machine learning in bolstering the wholesale sector and establish a foundation for subsequent research.