Development of Cargo Delivery Time Prediction Models

Abstract

E-commerce stands out as the sales form with the fastest growth momentum with high sales volumes. Managing sales volumes efficiently is of great importance in maximizing customer satisfaction. By accurately predicting delivery times, effec-tive logistics optimization is achieved and customers are informed about how long it will take for their cargo to be delivered. In this study, it is aimed to develop cargo delivery time prediction models with machine learning-based Categorical Boosting (CatBoost), Decision Tree (DT), Extreme Learning Machine (ELM), Light Gradient Boosting Machine (LightGBM) and Support Vector Machine (SVM). The 5113-row dataset contains delivery history information for the 16-month period between February 14, 2019, and June 13, 2020. The performance of the developed models has been evaluated using Mean Absolute Percentage Error (MAPE) by utilizing 5-fold cross-validation on the dataset. The results show that the models developed using SVM exhibited the most successful prediction performance.

Keywords

• Delivery Time Prediction
• Machine Learning
• E-Commerce

References

1. [1] Nodirovna, M. S., & Sharif oʻg‘li, A. S. (2024). E-Commerce Trends: Shaping The Future of Retail. Open Herald: Peri-odical of Methodical Research, 2(3), 46-49.
2. [2] Muñoz-Villamizar, A., Velázquez-Martínez, J. C., Haro, P., Ferrer, A., & Mariño, R. (2021). The environmental impact of fast shipping ecommerce in inbound logistics operations: A case study in Mexico. Journal of Cleaner Production, 283, 125400.
3. [3] Cui, R., Lu, Z., Sun, T., & Golden, J. M. (2024). Sooner or later? Promising delivery speed in online retail. Manufacturing & Service Operations Management, 26(1), 233-251.
4. [4] Özdemir, R., Taşyürek, M., & Aslantaş, V. (2024). Improved Marine Predators Algorithm and Extreme Gradient Boost-ing (XGBoost) for shipment status time prediction. Knowledge-Based Systems, 111775.
5. [5] Zhang, L., Liu, Y., Zeng, Z., Cao, Y., Wu, X., Xu, Y., ... & Cui, L. (2024). Package Arrival Time Prediction via Knowledge Distillation Graph Neural Network. ACM Transactions on Knowledge Discovery from Data, 108: 1–19.
6. [6] Zhang, L., Wu, X., Liu, Y., Zhou, X., Cao, Y., Xu, Y., ... & Miao, C. (2024). Estimating package arrival time via hetero-geneous hypergraph neural network. Expert Systems with Applications, 238, 121740.
7. [7] [Guo, B., Zuo, W., Wang, S., Zhou, X., & He, T. (2023). Attention Enhanced Package Pick-Up Time Prediction via Het-erogeneous Behavior Modeling. In International Conference on Algorithms and Architectures for Parallel Pro-cessing Singa-pore: Springer Nature Singapore,189-208.
8. [8] Hamdan, I. K., Aziguli, W., Zhang, D., & Sumarliah, E. (2023). Machine learning in supply chain: prediction of real-time e-order arrivals using ANFIS. International Journal of System Assurance Engineering and Management, 14,Suppl 1, 549-568.

9. [9] Zhang, L., Zhou, X., Zeng, Z., Cao, Y., Xu, Y., Wang, M., ... & Shen, Z. (2023). Delivery time prediction using large-scale graph structure learning based on quantile regression. In 2023 IEEE 39th International Conference on Data Engi-neering, IEEE, 3403-3416.
10. [10] Zhou, X., Wang, J., Liu, Y., Wu, X., Shen, Z., & Leung, C. (2023). Inductive graph transformer for delivery time estima-tion. In Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, 679-687.
11. [11] İnaç, H., Ayözen, Y. E., Atalan, A., & Dönmez, C. Ç. (2022). Estimation of postal service delivery time and energy cost with e-scooter by machine learning algorithms. Applied Sciences, 12(23), 12266.
12. [12] Salari, N., Liu, S., & Shen, Z. J. M. (2022). Real-time delivery time forecasting and promising in online retailing: When will your package arrive?. Manufacturing & Service Operations Management, 24(3), 1421-1436.
13. [13] Wen, H., Lin, Y., Mao, X., Wu, F., Zhao, Y., Wang, H., ... & Wan, H. (2022). Graph2route: A dynamic spatial-temporal graph neural network for pick-up and delivery route prediction. In Proceedings of the 28th ACM SIGKDD Conference On Knowledge Discovery and Data Mining, 4143-4152.
14. [14] Salcedo‐Sanz, S., Rojo‐Álvarez, J. L., Martínez‐Ramón, M., & Camps‐Valls, G. (2014). Support vector machines in engi-neering: an overview. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 4(3), 234-267.
15. [15] Barros, F. S., Cerqueira, V., & Soares, C. (2021). Empirical study on the impact of different sets of parameters of gradient boosting algorithms for time-series forecasting with LightGBM. In PRICAI 2021: Trends in Artificial Intelligence: 18th Pa-cific Rim International Conference on Artificial Intelligence, PRICAI 2021, Hanoi, Vietnam, November 8–12, 2021, Pro-ceedings, Part I 18, Springer International Publishing, 454-465.
16. [16] Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., & Gulin, A. (2018). CatBoost: unbiased boosting with cate-gorical features. Advances in neural information processing systems, 31.
17. [17] Wang J., Lu S., Wang S. H., Zhang Y. D. (2022), A review on extreme learning machine, Multimedia Tools and Applica-tions, 81(29), 41611-41660.
18. [18] Dabiri, H., Farhangi, V., Moradi, M. J., Zadehmohamad, M., & Karakouzian, M. (2022). Applications of decision tree and random forest as tree-based machine learning techniques for analyzing the ultimate strain of spliced and non-spliced rein-forcement bars. Applied Sciences, 12(10), 4851.
19. [19] URL https://www.kaggle.com/datasets/salil007/1-shipping-optimization-challenge?select=train_2_pr.csv