Global supply chains are increasingly characterized by volatility, complexity, and uncertainty, making accurate demand forecasting and efficient inventory management critical determinants of competitiveness. Traditional forecasting methods, often reliant on historical averages and static regression models, struggle to capture the nonlinear and rapidly shifting dynamics of consumer demand, market fluctuations, and external shocks. Predictive analytics models, grounded in statistical learning, data mining, and machine learning, have emerged as powerful tools to enhance demand forecasting accuracy and reduce inefficiencies in inventory management. These models leverage diverse data sources, including historical sales patterns, market signals, promotional calendars, social media sentiment, weather conditions, and macroeconomic indicators, to generate adaptive forecasts. Time series approaches such as ARIMA and exponential smoothing are increasingly complemented by advanced machine learning techniques like random forests, gradient boosting, and deep neural networks. Hybrid and real-time analytics models further improve forecast reliability by continuously integrating new data streams from IoT sensors, e-commerce platforms, and supply chain execution systems.By enhancing forecast accuracy, predictive analytics mitigates common inventory challenges such as overstocking, stockouts, and the bullwhip effect. Dynamic safety stock optimization, data-driven replenishment planning, and proactive identification of demand surges enable organizations to balance inventory levels more effectively. The resulting improvements extend beyond cost savings, encompassing greater operational agility, reduced lead times, and enhanced customer satisfaction. Case applications across retail, manufacturing, healthcare, and e-commerce demonstrate the transformative potential of predictive analytics in aligning supply with fluctuating demand. As supply chains evolve toward digital and autonomous ecosystems, predictive analytics will play a pivotal role in building resilience and sustainability. The convergence of artificial intelligence, big data, and prescriptive analytics will further enable organizations not only to anticipate demand with high accuracy but also to optimize decision-making for sustainable, adaptive, and resilient inventory management.