Machine Learning Approach: Consumer Buying Behavior Analysis

Abstract

The rise of multiple company competitors during the COVID-19 outbreak resulted in fierce competition among competing firms for new clients and the retention of current ones. As a result of the foregoing, exceptional customer service is required, regardless of the size of the organization. Furthermore, any company's ability to know each of its customers' desires will provide it an advantage when it comes to providing specialized customer care and establishing customized marketing plans for them. The term “Consumer Buying Behavior Analysis” refers to a comprehensive assessment of the company's ideal clients/customers. In this project, we're utilizing the K-Means Algorithm to divide clients into two groups: “Highly Active Customers” and “Least Active Customers.” Then, utilizing the Apriori Algorithm, we use Association Rule Mining to recommend the best goods to clients based on their purchasing history and associations. We take one step further and use Logistic Regression to validate our Clustering operation by doing Binary Classification with our clusters as the label, resulting in accuracy and an F1 score of 91%.