In today’s dynamic technological landscape, access to customer data has redefined traditional business paradigms. This shift requires companies to transition from product-centric to customer-centric models. This study delves into the fast-moving consumer goods (FMCG) retail sector, utilizing customer loyalty to precisely compute Customer Lifetime Value (CLV) through predictive methodologies based on decision trees. By integrating customer purchase and behavior analysis, this research establishes a framework for innovative product recommendation systems. Anticipating value fluctuations within a one-year horizon, this approach provides critical insights into customer behavior, empowering businesses to proactively manage marketing strategies and customer relationships, effectively mitigating potential revenue losses. The outcomes of this predictive model promise a substantial impact on the FMCG retail sector, offering a blueprint for optimizing decisions on product recommendations. Furthermore, this study presents significant financial contributions, representing a substantial opportunity for revenue recovery by leveraging customer behavior insights and personalized product recommendation strategies.