An AI-powered forecasting platform designed to accurately predict haulier capacity availability and transport demand in highly sparse, zero-inflated time series where conventional machine learning models typically fail. The platform incorporates a novel set of meta-ranking algorithms developed by the team to intelligently select and combine forecasting models, significantly improving prediction accuracy and robustness. It supports strategic planning, resource allocation, and demand management across logistics networks. The platform also serves as a companion API for the **Real-Time Haulier Capacities Tracking** system, enabling seamless integration between predictive and operational decision-support capabilities.
-
Main Gain(s): …
-
Start TRL: 0 - (evidences)
-
Final TRL: 0 - (evidences)
-
Main Contributions: (theoretics) E. Rocha; (implementation) J. Sousa, F. Vieira; (integration) J. Sousa
Main Features
- …
Videos
| Container Terminal Simulation Tool (demonstration of human configurations and KPI visualization without real-time data) |