Journal of Optimization and Supply Chain Management

Journal of Optimization and Supply Chain Management

Optimizing Freight Cost Predictions with a Hybrid GRU-GA Model: Implications for Supply Chain Sustainability

Document Type : Research Paper

Authors
Babak Javadi 1
Soroush Yousefi 2
1 Department of Industrial Engineering, Faculty of Engineering, College of Farabi, University of Tehran, Iran
2 Computational Optimization and Smart Transformation Lab, Faculty of Engineering, College of Farabi, University of Tehran, Qom, Iran
10.22034/ISS.2025.9056.1039
Abstract
Objective: Freight costs constitute a significant share of total supply chain expenses and play a critical role in operational efficiency and sustainability. Accurate freight cost forecasting is therefore essential for effective logistics planning and sustainable supply chain management. This study aims to develop a robust forecasting framework to improve the accuracy of freight cost prediction in real-world supply chain systems.
Methods: This research proposes a hybrid forecasting model that integrates a Gated Recurrent Unit (GRU) neural network with a Genetic Algorithm (GA) for hyperparameter optimization. The GRU model captures temporal dependencies in freight cost time-series data, while the GA optimizes key hyperparameters, including the number of neurons and dropout rate, by minimizing Mean Absolute Error (MAE). The model is trained and evaluated using a real-world healthcare supply chain dataset. Its performance is benchmarked against traditional statistical models, including Autoregressive (AR) and ARIMA models.
Results: The experimental results demonstrate that the proposed GRU-GA model significantly outperforms the benchmark models in terms of forecasting accuracy. The optimized GRU structure achieves lower MAE values compared to AR, ARIMA, and non-optimized deep learning models, indicating superior capability in modeling nonlinear and complex temporal patterns inherent in freight cost data.
Conclusion: The findings confirm that integrating evolutionary optimization with deep recurrent neural networks substantially enhances freight cost prediction performance. Improved forecasting accuracy can support better transportation planning, reduce operational inefficiencies, and contribute to economic, environmental, and social sustainability in supply chains. The proposed GRU-GA framework is flexible and can be extended to other logistics and transportation forecasting applications.
Keywords
supply chain sustainability
freight cost
deep learning
metaheuristics
genetic algorithm
Díaz-Ramírez, J., Zazueta-Nassif, S., Galarza-Tamez, R., Prato-Sánchez, D. & Huertas, J. I. (2023). Characterization of urban distribution networks with light electric freight vehicles. Transportation Research Part D: Transport and Environment, 119. https://doi.org/10.1016/j.trd.2023.103719      
Ehtesham Rasi, R. & Sohanian, M. (2020). A multi-objective optimization model for sustainable supply chain network with using genetic algorithm. Journal of Modelling in Management, 16(2). https://doi.org/10.1108/JM2-06-2020-0150
Jang, H. S., Chang, T. W. & Kim, S. H. (2023). Prediction of Shipping Cost on Freight Brokerage Platform Using Machine Learning. Sustainability (Switzerland) , 15(2). https://doi.org/10.3390/su15021122
Khajeh, E., Ramouz, A., Aminizadeh, E., Sabetkish, N., Golriz, M., Mehrabi, A. & Fonouni, H. (2023). Comparison of the Modified Piggyback with Standard Piggyback and Conventional Orthotopic Liver Transplantation Techniques: A Network Meta-Analysis. HPB, 25. https://doi.org/10.1016/j.hpb.2023.07.773
Kovács, G. (2017). First cost calculation methods for road freight transport activity. Transport and Telecommunication, 18(2). https://doi.org/10.1515/ttj-2017-0010
Mao, J., Cheng, J., Li, X., Zhao, H. & Lin, C. (2023). Optimal Design of Reverse Logistics Recycling Network for Express Packaging Considering Carbon Emissions. Mathematics, 11(4). https://doi.org/10.3390/math11040812
Panigrahi, S. S., Bahinipati, B. & Jain, V. (2019). Sustainable supply chain management: A review of literature and implications for future research. In Management of Environmental Quality: An International Journal (Vol. 30, Issue 5). https://doi.org/10.1108/MEQ-01-2018-0003
Sánchez-Flores, R. B., Cruz-Sotelo, S. E., Ojeda-Benitez, S. & Ramírez-Barreto, M. E. (2020). Sustainable supply chain management-A literature review on emerging economies. In Sustainability (Switzerland) (Vol. 12, Issue 17). https://doi.org/10.3390/SU12176972
Sternad, M. (2019). Cost calculation in road freight transport. Business Logistics in Modern Management, 1(1).
Tang, Z., Liu, X. & Wang, Y. (2020). Integrated Optimization of Sustainable Transportation and Inventory with Multiplayer Dynamic Game under Carbon Tax Policy. Mathematical Problems in Engineering, 2020. https://doi.org/10.1155/2020/4948383
Taş, D., Dellaert, N., Van Woensel, T. & De Kok, T. (2013). Vehicle routing problem with stochastic travel times including soft time windows and service costs. Computers and Operations Research, 40(1). https://doi.org/10.1016/j.cor.2012.06.008
Wang, J., Qiang, X., Ren, Z., Wang, H., Wang, Y. & Wang, S. (2023). Time-Series Well Performance Prediction Based on Convolutional and Long Short-Term Memory Neural Network Model. Energies, 16(1). https://doi.org/10.3390/en16010499
Saeed, N., Nguyen, S., Cullinane, K., Gekara, V., & Chhetri, P. (2023). Forecasting container freight rates using the       Prophet forecasting method. Transport Policy, 133, 86–107. https://doi.org/10.1016/j.tranpol.2023.01.012
Journal of Optimization and Supply Chain Management
Volume 2, Issue 2
Spring 2025
Pages 111-124