Comparative Performance Analysis using Machine Learning for Churn Prediction in E-commerce

Abstract

New clients cost a business significantly more money in e-commerce than keeping its existing clients. Companies can boost consumer retention, which will result in more revenue and faster growth, by anticipating which customers will quit. There are several products and solutions in today's competitive industry. Because of this, most clients are accustomed to quickly switching from one brand to another and from one supplier to another in their search for the best possible product or item to fulfill their requirements. This problem, known as "client churn," affects e-commerce enterprises. Due to their ability to process large volumes of data and recognize complex patterns, machine learning algorithms have emerged as a powerful tool for predicting client churn in recent years. Using a publicly accessible dataset, the proposed model examines various machine learning methods for predicting customer churn in this study. Also, by using performance metrics, the proposed model compares how well different algorithms perform.