Research Paper:
Research on Cross-Border e-Commerce Supply Chain Prediction and Optimization Model Based on Convolutional Neural Network Algorithm
Yajie Zhao*,
, Bin Gong**, and Bo Huang*
*Department of School of Business, Guangdong Polytechnic of Science and Technology
No.65 Zhuhai Avenue, Jinwan District, Zhuhai, Guangdong 519090, China
Corresponding author
**Department of Computer Engineering Technical College (Artificial Intelligence College), Guangdong Polytechnic of Science and Technology
No.65 Zhuhai Avenue, Jinwan District, Zhuhai, Guangdong 519090, China
Enhancing the precision of supply chain management and reducing operational costs are crucial for the development of the cross-border e-commerce market. However, existing research often overlooks the demand uncertainty caused by seasonal variations and the challenges of handling returns in logistics. Therefore, this paper proposes a SARIMA-CNN-BiLSTM prediction model that effectively captures both the seasonal and nonlinear characteristics of cross-border e-commerce supply chains. Additionally, by incorporating the returns process, a supply chain distribution optimization model is developed with the objective of minimizing total operational costs. The model is solved using an improved whale optimization algorithm. In validation with real-world data, the SARIMA-CNN-BiLSTM model achieved a mean absolute percentage error reduction of 6.479 and 7.703 compared to convolutional neural network (CNN) and BiLSTM models, respectively. Moreover, the chosen optimization algorithm reduced the cost by 231,310 CNY, 62,564 CNY, and 131,632 CNY compared to the whale optimization algorithm, genetic algorithm, and particle swarm optimization, respectively. The proposed approach provides robust support for cross-border e-commerce enterprises in reducing costs and enhancing efficiency in their operations.
- [1] H. Wu, Y. Qiao, and C. Luo, “Cross-border e-commerce, trade digitisation and enterprise export resilience,” Finance Research Letters, Vol.65, Article No.105513, 2024. https://doi.org/10.1016/j.frl.2024.105513
- [2] J. Sun, Z. Chen, Z. Chen, and X. Li, “Robust optimization of a closed-loop supply chain network based on an improved genetic algorithm in an uncertain environment,” Computers & Industrial Engineering, Vol.189, Article No.109997, 2024. https://doi.org/10.1016/j.cie.2024.109997
- [3] Y. Dai, L. Dou, H. Song, L. Zhou, and H. Li, “Two-way information sharing of uncertain demand forecasts in a dual-channel supply chain,” Computers & Industrial Engineering, Vol.169, Article No.108162, 2022. https://doi.org/10.1016/j.cie.2022.108162
- [4] A. Alonso-Ayuso, L. F. Escudero, M. Guignard, and A. Weintraub, “Risk management for forestry planning under uncertainty in demand and prices,” European J. of Operational Research, Vol.267, No.3, pp. 1051-1074, 2018. https://doi.org/10.1016/j.ejor.2017.12.022
- [5] Y. Tadayonrad and A. B. Ndiaye, “A new key performance indicator model for demand forecasting in inventory management considering supply chain reliability and seasonality,” Supply Chain Analytics, Vol.3, Article No.100026, 2023. https://doi.org/10.1016/j.sca.2023.100026
- [6] R. Carbonneau, K. Laframboise, and R. Vahidov, “Application of machine learning techniques for supply chain demand forecasting,” European J. of Operational Research, Vol.184, No.3, pp. 1140-1154, 2008. https://doi.org/10.1016/j.ejor.2006.12.004
- [7] M. M. Vali-Siar and E. Roghanian, “Sustainable, resilient and responsive mixed supply chain network design under hybrid uncertainty with considering COVID-19 pandemic disruption,” Sustainable Production and Consumption, Vol.30, pp. 278-300, 2022. https://doi.org/10.1016/j.spc.2021.12.003
- [8] K. Swaminathan and R. Venkitasubramony, “Demand forecasting for fashion products: A systematic review,” Int. J. of Forecasting, Vol.40, No.1, pp. 247-267, 2024. https://doi.org/10.1016/j.ijforecast.2023.02.005
- [9] M. Zheng, K. Wu, and Y. Shu, “Newsvendor problems with demand forecast updating and supply constraints,” Computers & Operations Research, Vol.67, pp. 193-206, 2016. https://doi.org/10.1016/j.cor.2015.10.007
- [10] L. Cui, Y. Chen, J. Deng, and Z. Han, “A novel attLSTM framework combining the attention mechanism and bidirectional LSTM for demand forecasting,” Expert Systems with Applications, Vol.254, Article No.124409, 2024. https://doi.org/10.1016/j.eswa.2024.124409
- [11] C.-Y. Chiang, W. T. Lin, and N. C. Suresh, “An empirically-simulated investigation of the impact of demand forecasting on the bullwhip effect: Evidence from U.S. auto industry,” Int. J. of Production Economics, Vol.177, pp. 53-65, 2016. https://doi.org/10.1016/j.ijpe.2016.04.015
- [12] A.-K. Kähkönen, K. Marttinen, A. Kontio, and K. Lintukangas, “Practices and strategies for sustainability-related risk management in multi-tier supply chains,” J. of Purchasing and Supply Management, Vol.29, No.3, Article No.100848, 2023. https://doi.org/10.1016/j.pursup.2023.100848
- [13] D. Prak and R. Teunter, “A general method for addressing forecasting uncertainty in inventory models,” Int. J. of Forecasting, Vol.35, No.1, pp. 224-238, 2019. https://doi.org/10.1016/j.ijforecast.2017.11.004
- [14] L. Ye, N. Xie, J. E. Boylan, and Z. Shang, “Forecasting seasonal demand for retail: A Fourier time-varying grey model,” Int. J. of Forecasting, Vol.40, No.4, pp. 1467-1485, 2024. https://doi.org/10.1016/j.ijforecast.2023.12.006
- [15] N. Hasan, N. Ahmed, and S. M. Ali, “Improving sporadic demand forecasting using a modified k-nearest neighbor framework,” Engineering Applications of Artificial Intelligence, Vol.129, Article No.107633, 2024. https://doi.org/10.1016/j.engappai.2023.107633
- [16] W. I. Y. Keller, B. Deleersnyder, and K. Gedenk, “Price promotions and popular events,” J. of Marketing, Vol.83, No.1, pp. 73-88, 2019. https://doi.org/10.1177/0022242918812055
- [17] F. Petropoulos et al., “Forecasting: Theory and practice,” Int. J. of Forecasting, Vol.38, No.3, pp. 705-871, 2022. https://doi.org/10.1016/j.ijforecast.2021.11.001
- [18] T. R. Willemain, C. N. Smart, and H. F. Schwarz, “A new approach to forecasting intermittent demand for service parts inventories,” Int. J. of Forecasting, Vol.20, No.3, pp. 375-387, 2004. https://doi.org/10.1016/S0169-2070(03)00013-X
- [19] M. Rodrigues, V. Miguéis, S. Freitas, and T. Machado, “Machine learning models for short-term demand forecasting in food catering services: A solution to reduce food waste,” J. of Cleaner Production, Vol.435, Article No.140265, 2024. https://doi.org/10.1016/j.jclepro.2023.140265
- [20] H. Hafizh, A. H. A. Rasib, R. Abdullah, M. H. A. Bakar, and A. M. Kassim, “Application of convolutional neural networks for binary recognition task of two similar industrial machining parts,” Int. J. of Advanced Computer Science and Applications, Vol.12, No.9, pp. 403-410, 2021. https://doi.org/10.14569/IJACSA.2021.0120946
- [21] J. Wang, C. L. E. Swartz, and K. Huang, “Deep learning-based model predictive control for real-time supply chain optimization,” J. of Process Control, Vol.129, Article No.103049, 2023. https://doi.org/10.1016/j.jprocont.2023.103049
- [22] R. Mastragostino, S. Patel, and C. L. E. Swartz, “Robust decision making for hybrid process supply chain systems via model predictive control,” Computers & Chemical Engineering, Vol.62, pp. 37-55, 2014. https://doi.org/10.1016/j.compchemeng.2013.10.019
- [23] S. Pang et al., “Collaborative power tracking method of diversified thermal loads for optimal demand response: A MILP-based decomposition algorithm,” Applied Energy, Vol.327, Article No.120006, 2022. https://doi.org/10.1016/j.apenergy.2022.120006
- [24] A. Saif and E. Delage, “Data-driven distributionally robust capacitated facility location problem,” European J. of Operational Research, Vol.291, No.3, pp. 995-1007, 2021. https://doi.org/10.1016/j.ejor.2020.09.026
- [25] S. Niu, G. Sun, and G. Yang, “Distributionally robust optimization for a capacity-sharing supply chain network design problem,” J. of Cleaner Production, Vol.447, Article No.141563, 2024. https://doi.org/10.1016/j.jclepro.2024.141563
- [26] H. Yu and W. D. Solvang, “A fuzzy-stochastic multi-objective model for sustainable planning of a closed-loop supply chain considering mixed uncertainty and network flexibility,” J. of Cleaner Production, Vol.266, Article No.121702, 2020. https://doi.org/10.1016/j.jclepro.2020.121702
- [27] F. Goodarzian, S. F. Wamba, K. Mathiyazhagan, and A. Taghipour, “A new bi-objective green medicine supply chain network design under fuzzy environment: Hybrid metaheuristic algorithms,” Computers & Industrial Engineering, Vol.160, Article No.107535, 2021. https://doi.org/10.1016/j.cie.2021.107535
- [28] L. A. Menéndez-García, P. J. García-Nieto, E. García-Gonzalo, and F. Sánchez Lasheras, “Time series analysis for COMEX platinum spot price forecasting using SVM, MARS, MLP, VARMA and ARIMA models: A case study,” Resources Policy, Vol.95, Article No.105148, 2024. https://doi.org/10.1016/j.resourpol.2024.105148
- [29] C. Xiong et al., “EMD-FFT-SARIMA photovoltaic power generation prediction model using fast Fourier transform optimization cycle parameters,” High Power Laser and Particle Beams, Vol.36, No.8, Article No.085001, 2024 (in Chinese). https://doi.org/10.11884/HPLPB202436.230349
- [30] Ravikumar R. N., S. Jain, and M. Sarkar, “LSTM-GNOG: A new paradigm to address cold start movie recommendation system using LSTM with Gaussian Nesterov’s optimal gradient,” Int. J. of Advanced Computer Science and Applications, Vol.15, No.6, pp. 746-755, 2024. https://doi.org/10.14569/IJACSA.2024.0150675
- [31] S. Seo and M. Chung, “Evaluation of applicability of 1D-CNN and LSTM to predict horizontal displacement of retaining wall according to excavation work,” Int. J. of Advanced Computer Science and Applications, Vol.13, No.2, pp. 86-91, 2022. https://doi.org/10.14569/IJACSA.2022.0130210
- [32] B. Liang et al., “A novel framework for predicting non-stationary production time series of shale gas based on BiLSTM-RF-MPA deep fusion model,” Petroleum Science, Vol.21, No.5, pp. 3326-3339, 2024. https://doi.org/10.1016/j.petsci.2024.05.012
- [33] S. Bandhekar et al., “Optimizing industrial engineering performance with fuzzy CNN framework for efficiency and productivity,” Int. J. of Advanced Computer Science and Applications, Vol.15, No.6, pp. 1250-1257, 2024. https://doi.org/10.14569/IJACSA.2024.01506126
- [34] M. R. Sahib, H. Elkina, and T. Zaki, “From technical indicators to trading decisions: A deep learning model combining CNN and LSTM,” Int. J. of Advanced Computer Science and Applications, Vol.15, No.6, pp. 847-855, 2024. https://doi.org/10.14569/IJACSA.2024.0150685
- [35] K. He, L. Ji, C. W. D. Wu, and K. F. G. Tso, “Using SARIMA–CNN–LSTM approach to forecast daily tourism demand,” J. of Hospitality and Tourism Management, Vol.49, pp. 25-33, 2021. https://doi.org/10.1016/j.jhtm.2021.08.022
- [36] Y. Han et al., “Two-stage heuristic algorithm for vehicle-drone collaborative delivery and pickup based on medical supplies resource allocation,” J. of King Saud University – Computer and Information Sciences, Vol.35, No.10, Article No.101811, 2023. https://doi.org/10.1016/j.jksuci.2023.101811
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.