Abstract—Today’s global economy can operate efficiently due to timely and cost-effective delivery of goods. There are a huge number of shipping companies on the market, whose sole purpose is to transport the ordered goods. Road transportation can be carried out using the company’s own fleet of trucks or using third-party companies. This work focuses on Full Truckload (FTL) transportation. The shipper must be aware of the potential costs of a given service during the process of selecting the right service provider. Our solution analyzes the cost estimation of the FTL shipping. Market offers many approaches, from detailed calculators to solutions using various Artificial Intelligence (AI) solutions. This study compares hybrid solutions that combine different Machine Learning (ML) techniques. The solution is tested on real data covering multi-year contracts of several freight forwarding companies operating in the European FTL market. The results obtained are implemented in a commercial solution used by freight forwarding companies daily.
 
Keywords—regression, clustering, cost estimation, Full Truckload (FTL), k-Nearest Neighbors (k-NN), eXtreme Gradient Boosting (XGBoost), Density-Based Spatial Clustering of Applications with Noise (DBSCAN)


Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.