Machine learning-driven prediction of cost-efficient shipping lines: evidence from freight forwarding operations

Muhammad Aref Arfeen, Nermine Khalifa, Hatem Abdelkader

Abstract


Purpose
This research evaluates the performance of various machine learning models in forecasting cost-efficient transportation lines from the viewpoint of freight forwarders. It addresses the requirement for data-informed decision-support tools that can enhance the precision of shipment line selection.

Design/Methodology/Approach
A dataset comprising 983 shipment records from 37 freight-forwarding companies in Egypt was examined. Six machine learning models Naive Bayes, K-Nearest Neighbour, Support Vector Machines, Decision Trees, Random Forests, and Neural Networks were trained and assessed employing an 80/20 train-test partition. The performance of the model was evaluated utilizing accuracy, precision, recall, and F1-score.

Findings
Random Forests and Decision Trees achieved the finest predictive performance, with accuracy scores of 0.83 and 0.80, respectively. K-Nearest Neighbour exhibited moderate performance, whereas Naive Bayes and Neural Networks demonstrated comparatively lower predictive accuracy. Support Vector Machines demonstrated suboptimal performance across all evaluated metrics. The findings suggest that ensemble and tree-based methodologies are highly appropriate for modeling the cost efficacy of shipping lines.

Research Implications/Limitations

The research emphasizes the significance of model selection in logistics forecasting tasks and demonstrates that more complex or computationally demanding models do not necessarily surpass the performance of simplified tree-based approaches. The dataset is restricted to shipments originating from Egypt in 2022, which may impact its overall generalizability.

Practical Implications

The findings provide freight forwarders with a foundation for incorporating machine learning into their operational decision-support systems. Utilizing Random Forests or Decision Trees can improve the precision of shipping line selection, lower expenses, and facilitate data-driven logistics planning.
Originality
The study offers a comparative analysis of various machine learning methods specifically applied to the selection of transportation lines a subject with limited prior exploration. It provides empirical evidence on the predictive models that most effectively aid in making freight-forwarding decisions related to cost efficiency.

 

Received 14 November 2025

Accepted 08 January 2026

Published 05 May 2026


Full Text:

PDF

References


Alireza Ermagun, Aymeric Punel and Stathopoulos, A. (2020). Shipment status prediction in online crowd-sourced shipping platforms. Sustainable Cities and Society, 53. doi:https://doi.org/10.1016/j.scs.2019.101950.

Ayfer Ergin and Alkan, G. (2023). The selection of ocean container carrier: An analytic network process (ANP) approach. Journal of ETA Maritime Science, 11(3), pp.159–167. doi:https://doi.org/10.4274/jems.2023.96977.

Birkel, H., Matthias Kopyto and Lutz, C. (2020). Challenges of applying predictive analytics in transport logistics. ACM, pp.144–151. doi:https://doi.org/10.1145/3378539.3393864.

Calixto, N. and Ferreira, J. (2020). Salespeople performance evaluation with predictive analytics in B2B. Applied Sciences, 10(11), p.4036. doi:https://doi.org/10.3390/app10114036.

Cao, K. (2022). A machine learning-based approach to railway logistics transport path optimization. Mathematical Problems in Engineering, 2022, pp.1–11. doi:https://doi.org/10.1155/2022/1691215.

Christos Gkerekos, Iraklis Lazakis and Gerasimos Theotokatos (2019). Machine learning models for predicting ship main engine Fuel Oil Consumption: A comparative study. Ocean Engineering, 188, p.106282. doi:https://doi.org/10.1016/j.oceaneng.2019.106282.

D Rajasekar and Prabhakar, T.Sandeep. (2015). Importance of freight forwarding and work activities of freight forwarders-an empirical analysis. 250 X Indian Journal of Applied Research, 5(1).

Ding, J.-F., Dye, C.-Y., Liang, S.-Y., Chou, C.-C., Tseng, W.-J. and Shyu, W.-H. (2017). Evaluating key factors influencing the development of multi-country consolidation for ocean freight forwarders in Taiwan. Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment, 231(1), pp.342–352. doi:https://doi.org/10.1177/1475090215621577.

Egemen Sert, Hedayatifar, L., Rigg, R.A., Akhavan, A., Buchel, O., Saadi, D.E., Kar, A.A., Morales, A.J. and Yaneer Bar-Yam (2020). Freight time and cost optimization in complex logistics networks. Complexity, 2020, pp.1–11. doi:https://doi.org/10.1155/2020/2189275.

Fanam, P.D., Nguyen, H.O. and Cahoon, S. (2018). An empirical analysis of the critical selection criteria of liner operators: The perspective of freight forwarders. International Journal of Shipping and Transport Logistics, 10(5-6). doi:https://doi.org/10.1504/ijstl.2018.095222.

FIATA (2019). FIATA model rules for freight forwardering services. Glattbrugg.

Hicks, S.A., Strümke, I., Vajira Thambawita, Malek Hammou, Riegler, M.A., Halvorsen, P. and Sravanthi Parasa (2022). On evaluation metrics for medical applications of artificial intelligence. Scientific Reports, 12(1), p.5979. doi:https://doi.org/10.1038/s41598-022-09954-8.

Ho, T.C., Chiu, R.H., Chung, C.C. and Lee, H.S. (2017). Key influence factors for ocean freight forwarders selecting container shipping lines using the revised dematel approach. Journal of Marine Science and Technology (Taiwan), 25(3). doi:https://doi.org/10.6119/JMST-016-1227-1.

Huang, S.T., Emrah Bulut and Duru, O. (2019). Service quality evaluation of international freight forwarders: an empirical research in East Asia. Journal of Shipping and Trade, 4(1), p.14. doi:https://doi.org/10.1186/s41072-019-0053-6.

Jang, H.-S., Chang, T.-W. and Kim, S.-H. (2023). Prediction of shipping cost on freight brokerage platform using machine learning. Sustainability, 15(2), p.1122. doi:https://doi.org/10.3390/su15021122.

Jussi Tohka and Gils, M. van (2021). Evaluation of machine learning algorithms for health and wellness applications: A tutorial. Computers in Biology and Medicine, 132, p.104324. doi:https://doi.org/10.1016/j.compbiomed.2021.104324.

Kotenko, V. (2022). Application of algorithmic models of machine learning to the freight transportation process. Transport technologies, 2022(2), pp.10–21. doi:https://doi.org/10.23939/tt2022.02.010.

Lukinskiy, V. and Vladislav Lukinskiy (2015). Analysis of the logistics intermediaries choice methods in the supply chains. Transport and Telecommunication Journal, 16(4), pp.288–295. doi:https://doi.org/10.1515/ttj-2015-0026.

Raj Bridgelall (2024). Locating electrified aircraft service to reduce urban congestion. Information, 15(4), p.186. doi:https://doi.org/10.3390/info15040186.

Rao, D., Chandra, D. and Kumar, D. (2017). A survey on machine learning: Concept, algorithms and applications’. International Conference on Innovative Research in Computer and Communication Engineering.

Ron, Feelders, A.J. and Hennie (2015). Uncovering document fraud in maritime freight transport based on probabilistic classification. In: K. Saeed and Wladyslaw Homenda, eds. Springer International Publishing. doi:https://doi.org/10.1007/978-3-319-24369-6.

Saraswathi Hathikal, Chung, S.H. and Karczewski, M. (2020). Prediction of ocean import shipment lead time using machine learning methods. SN Applied Sciences, 2(7), p.1272. doi:https://doi.org/10.1007/s42452-020-2951-5.

Shang, Y., Dunson, D. and Song, J.-S. (2017). Exploiting big data in logistics risk assessment via bayesian nonparametrics. Operations Research, 65(6), pp.1574–1588. doi:https://doi.org/10.1287/opre.2017.1612.

Szymon Cyperski, Michał Okulewicz and Domański, P.D. (2024). On cost estimation of the full truckload contracts. Journal of Advances in Information Technology, 15(5), pp.614–621. doi:https://doi.org/10.12720/jait.15.5.614-621.

Tri Wahyudi and Dava Septya Arroufu (2022). IMPLEMENTATION OF DATA MINING PREDICTION DELIVERY TIME USING LINEAR REGRESSION ALGORITHM. Journal of Applied Engineering and Technological Science, 4(1). doi:https://doi.org/10.37385/jaets.v4i1.918.

Uddin, M., Sabreena Anowar and Naveen Eluru (2021). Modeling freight mode choice using machine learning classifiers: a comparative study using Commodity Flow Survey (CFS) data. Transportation Planning and Technology, 44(5), pp.543–559. doi:https://doi.org/10.1080/03081060.2021.1927306.

Zhou, Y., Chen, W., Sun, X. and Yang, D. (2023). Early warning of telecom enterprise customer churn based on ensemble learning. PLOS ONE, 18(10), p.e0292466. doi:https://doi.org/10.1371/journal.pone.0292466.




DOI: https://dx.doi.org/10.21622/IBL.2026.06.1.1795

Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Muhammad Aref Arfeen, Nermine Khalifa, Hatem Abdelkader

International Business Logistics

E-ISSN: 2735-5969

P-ISSN: 2735-5950

 

Published by:

Academy Publishing Center (APC)

Arab Academy for Science, Technology and Maritime Transport (AASTMT)

Alexandria, Egypt

ibl@aast.edu