Manuscript received September 1, 2023; revised December 18, 2023; accepted March 22, 2024; Published July 29, 2024
Abstract—Shipping of the goods is crucial for the development of the present economy. The transportation may be realized in many ways. This work focuses on the Full Truck Load (FTL) road transportation model. Such services are often realized using external fleet, and then there is a need for a tool that compares such offers, i.e. which allows to estimate the desired shipping cost. Generally, the FTLs fit to the long range routes. Estimation of such contracts is common and can be realized with different approaches, like calculators or sophisticated machine learning solutions. Apart of that, the need for the shipment cost estimation is also required for short and very short routes, which frequently support long routes. The rules for pricing of the FTL short routes differs from the long ones and thus the approaches used differ as well. This work presents custom approach specifically focused on that task. The assessment is performed using real multi-year contract data of several shipping companies operating in the European market.
Keywords—cost estimation, full truck loads, machine learning, regression, clustering, DBSCAN
Cite: Jakub Gruszecki, Wojciech Szerszeń, Szymon Cyperski, and Paweł D. Domański, "Custom Approach to the Cost Estimation of the Full Truckload Contracts for Short Routes," International Journal of Machine Learning vol. 14, no. 3, pp. 70-76, 2024.
Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).