International Journal of Management

Customer Lifetime Value (CLV) measures the total economic contribution of a customer over the entire relationship period. While traditional CLV models rely on deterministic statistical approaches, global digital ecosystems now require predictive, real-time models that incorporate cross-border behavior, multi-cultural purchasing patterns, and platform-specific interactions. Machine learning (ML) enables dynamic CLV estimation using transaction history, behavioral signals, engagement metrics, and demographic diversity across markets. This research synthesizes approaches from marketing analytics, machine learning, and international consumer behavior to propose the Global CLV Prediction Model (G-CLVPM). The framework integrates hybrid algorithms such as Gradient Boosting, Bayesian Survival Models, LSTM, and Reinforcement Learning to forecast CLV in global scenarios. The study includes case analyses from streaming platforms, e-commerce networks, fintech ecosystems, and multinational loyalty programs.