Amazon uses deep learning algorithms to generate demand forecasts for over 400 million products daily, predicting how much of each item to stock in which fulfillment centers — reducing excess inventory, preventing stockouts, and enabling faster delivery.

Amazon's forecasting has evolved through multiple generations of machine learning models, from random forests to transformer-based architectures drawn from natural language processing research. In June 2025, Amazon announced a new foundational AI forecasting model that ingests hundreds of millions of product-level data points daily, blending historical sales, weather patterns, and holiday schedules to predict demand with greater precision. The system enables Amazon to pre-position inventory closer to likely buyers, underpinning its ability to offer same-day and next-day delivery at scale. In 2024, Amazon delivered over 9 billion items same-day or next-day globally.