Predictive and Prescriptive Logistics Optimization Using Hybrid AI, Time-Series Analytics, and Synthetic Data: A Case Study

Abstract

Global logistics networks face increasing volatility driven by geopolitical tensions, climate disruptions, demand variability, and operational uncertainty. Although artificial intelligence has improved predictive capabilities in logistics, classical and standalone learning models remain limited by data sparsity, non-stationarity, and scalability constraints. This study proposes a hybrid logistics intelligence framework that integrates time-series forecasting, synthetic data generation, and AI-based optimization. The framework is designed to enhance forecasting robustness and translate predictions into actionable operational decisions. A FedEx case study demonstrates how historical shipment data, real-time telemetry, and synthetically generated disruption scenarios can be jointly leveraged to improve demand forecasting, routing efficiency, and service reliability. Performance is evaluated across real, simulated, and hybrid datasets. Results show that the proposed approach consistently outperforms traditional statistical and machine-learning methods in accuracy, robustness, and operational scalability.