AI-supported Forecasting of Intermodal Freight Transportation Delivery Time

In recent years, the ever-increasing demand of e-commerce has led to the creation and development of projects related to international freight transportation, using machine learning techniques in order to handle field challenges. The purpose of this work is to forecast the critical time interval cases from warehouses to delivery points between: (a) order and pickup, (b) pickup and ETA delivery and (c) pickup and ATA delivery of an international freight transportation company, utilizing and comparing several machine learning techniques suitable for regression problems. Four machine learning techniques are utilized: Random Forest, Gradient Boosting, WaveNet and Bagging. In order to decide for the method or methods with the best predictive performance, Monte-Carlo simulations were performed for each technique. Simulation results show that Gradient Boosting and Bagging techniques have achieved the best predictions of time intervals for most of the examined cases.