Toward Reducing Unproductive Container Moves: Predicting Service Requirements and Dwell Times

Researchers from Tecnológico de Monterrey and a Veracruz container terminal developed ML models to reduce unproductive moves by predicting which containers need pre-clearance services and estimating dwell times. Models trained on historical operational data consistently outperformed rule-based heuristics. Results provide practical inputs for strategic yard planning and resource allocation.