Customer Lifetime Value Modeling: A Machine Learning Approach to Customer Segmentation By K-Means and Xgboost

Abstract

This research utilizes advanced machine learning models to predict Customer Lifetime Value (CLV). Customer Lifetime Value (CLV) is a key business metric that estimates the total revenue a business can reasonably expect from a single customer throughout the entirety of its relationship with the company. It helps businesses understand how much each customer is worth, enabling them to make informed decisions about customer acquisition, retention strategies, and resource allocation. The research applies k-means algorithm to segment customers into distinct groups, and the XGBoost algorithm to predict CLV, offering insights into customer patterns that can enhance marketing strategies. A comparative analysis of XGBoost and K-Nearest Neighbors (K-NN) demonstrates the superior performance of XGBoost in handling complex data relationships and non-linear patterns. The results also demonstrate that using K-Means and XGBoost together makes segmentation and CLV prediction more effective, achieving a 99% classification accuracy. It provides a helpful framework for businesses to improve customer retention and profits. Moreover, focusing on ethical data usage and sustainable business practices, the research highlights the social, environmental, and ethical aspects of using machine learning in customer management.