Machine Learning Forecasts of Spot Truckload Prices Using Operational Carrier Data: A Comparative Study of XGBoost and Benchmark Models
Main Article Content
Abstract
This article creates and assesses a supervX`ised machine learning model in order to forecast spot truckload rates at the shipment level, this paper. We create a feature set with lane information, shipment date, distance, and cargo weight using operational data from carriers for 2022–2024. The target is defined as freight cost in USD per load and rate per mile. A global mean model, a lane mean model, multiple linear regression, random forest, and an XGBoost ensemble are the five methods we benchmark after formulating the problem as a regression task.
Article Details
Issue
Section
How to Cite
References
1. J.W. Miller, “ARIMA Time Series Models for Full Truckload Transportation Prices,” Forecasting, vol. 1, no. 1, pp. 121–134, 2019.
2. A. Budak, A. Ustundag, B. Guloglu, “A Forecasting Approach for Truckload Spot Market Pricing,” Transportation Research Part A: Policy and Practice, vol. 97, pp. 55–68, 2017.
3. A. Budzyński, M. Cieśla, “Application of a Machine Learning Model for Forecasting Freight Rate in Road Transport,” Scientific Journal of Silesian University of Technology, Series Transport, vol. 126, pp. 23–48, 2025.
4. A. Budzyński, “Enhancing Road Freight Price Forecasting Using Gradient Boosting Machines,” Mathematics, vol. 13, no. 18, article 2964, 2025.
5. T. Green, A. Rokoss, K. Kramer, M. Schmidt, “Application of Machine Learning on Transport Spot Rate Prediction in the Recycling Industry,” in Proceedings of the Conference on Production Systems and Logistics (CPSL 2022), pp. 554–563, 2022.
6. B. Mrówczyńska, M. Cieśla, A. Król, A. Sładkowski, “Application of Artificial Intelligence in Prediction of Road Freight Transportation,” Promet – Traffic & Transportation, vol. 29, no. 4, pp. 363–370, 2017.
7. J.W. Miller, A. Scott, B.D. Williams, “Pricing Dynamics in the Truckload Sector: The Moderating Role of the Electronic Logging Device Mandate,” Journal of Business Logistics, vol. 42, no. 4, pp. 388–405, 2021.
8. H. Bousqaoui, S. Achchab, K. Tikito, “Machine Learning Applications in Supply Chains: An Emphasis on Neural Network Applications,” in Proc. 2017 3rd Int. Conf. on Cloud Computing Technologies and Applications (CloudTech), pp. 1–7, 2017.
9. T. Chen, C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), pp. 785–794, 2016.
10. L. Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
11. Y. LeCun, Y. Bengio, G. Hinton, “Deep Learning,” Nature, vol. 521, pp. 436–444, 2015.
12. W.B. Powell, “Maximizing Profits for North American Van Lines’ Truckload Division,” Interfaces, vol. 18, no. 1, pp. 21–41, 1988.
13. V. Ram, “Use Machine Learning to Forecast Trucking Rates,” Penske Logistics, online article, approx. 2018–2019 (accessed 2025).
14. Truckstop, “Understanding Spot Freight Rates,” Truckstop.com, online article, Apr. 5, 2022 (accessed 2025).
15. Flock Freight, “Using Trucking Spot Rates to Find Higher-Paying Loads,” FlockFreight.com, online article, May 9, 2023 (accessed 2025)