Predictive Modeling of Customer Satisfaction in Computer Hardware Product Returns: A Case Study in Bengaluru, India

Abstract

Reverse logistics, particularly in the realm of computer product returns, has become a critical factor in modern business operations. With the rapid expansion of e-commerce, businesses must navigate the complexities of return policies to maintain both customer satisfaction and operational efficiency. This study examines the impact of consumer satisfaction with return policies for computer products in Bengaluru, India, a major technology hub. By employing a quantitative research approach, data from 223 customers were collected and analyzed using various machine learning models, including Random Forest, K-Nearest Neighbors, Logistic Regression, and Support Vector Machines. The study identifies key factors influencing customer satisfaction and determines the best-performing model for predicting consumer behavior related to product returns. Findings highlight significant influences such as ease of return, processing time, payment methods, and competition from alternative providers. The research provides actionable insights for businesses to optimize their reverse logistics strategies, enhance customer satisfaction, and foster long-term loyalty in the competitive e-commerce landscape.