Predicting Customer Lifetime Value: A Data-Driven Case Study of Myntra

In today’s dynamic digital economy, customer-centric strategies play a critical role in sustaining e-commerce competitiveness. One of the most effective ways to assess customer profitability is through the prediction of Customer Lifetime Value (CLV)—a forward-looking metric that estimates the total net profit a business can expect from a customer throughout their entire relationship. This research paper develops a predictive model for CLV using simulated transactional data that reflects the behavioral patterns typical of customers on Myntra, one of India’s largest fashion e-commerce platforms. Leveraging RFM (Recency, Frequency, Monetary) analysis and Multiple Linear Regression, the study achieves a strong predictive performance with an R² score of 0.78. Results confirm that Recency is negatively associated with CLV, while Frequency and Monetary value exhibit strong positive correlations. The study not only provides a scalable, interpretable model but also delivers strategic recommendations for segmentation, marketing personalization, and resource optimization. This paper reinforces the importance of applying data analytics in digital retail to foster profitability and customer retention.