Data-Driven Optimization of Customer Acquisition Cost: A Business Model Based on Predictive and Prescriptive Analytics

This study presents a data-driven framework for optimizing Customer Acquisition Cost (CAC), a key metric for evaluating marketing and operational efficiency. Drawing on a comprehensive dataset from North American supermarkets, the research applies machine learning and segmentation analysis to identify the primary factors influencing CAC. The findings reveal that promotional design and media strategy significantly affect acquisition costs, while store format and amenities offer secondary leverage. A predictive business model is proposed, integrating store characteristics, geographic context, and promotional variables to guide marketing allocation. The results offer actionable insights for businesses aiming to reduce CAC, enhance scalability, and support financial planning through advanced analytics.