This open access book provides a cutting-edge framework for leveraging data-driven predictions to solve complex operational problems in platform-based supply chains. It moves beyond traditional models by integrating advanced machine learning with optimization techniques, enabling managers to make smarter, more adaptive decisions in dynamic digital environments.
The approach bridges the gap between predictive analytics and operational decision-making, introducing a structured “predict-then-optimize” methodology tailored for platform ecosystems. This dual focus allows for more robust and realistic solutions than purely deterministic or intuition-based approaches.
Key features and benefits include:
A unified framework that integrates prediction and optimization models for end-to-end supply chain decision-making;
Real-world case studies and examples that illustrate the application of the methodology in platform contexts;
Practical guidance on implementing predictive and optimization techniques using modern computational tools.

Yugang Yu is Yangtze Scholar Distinguished Professor of Operations Management at University of Science and Technology of China. His current research interests are logistics, supply chain management, and business analytics.

Shengming Zheng is an assistant professor at University of Science and Technology of China. His research interests include supply chain management and consumer behavior.

Ting Wang is a postdoctoral researcher at University of Science and Technology of China. Her research interests include business analytics and supply chain management.

Ye Shi is an associate professor at University of Science and Technology of China. His research focuses on supply chain analytics and IT innovation.