E-commerce warehousing and logistics optimization are crucial in meeting increased consumer demand, reducing costs, and improving operational efficiency. Previous work has applied machine learning and deep learning techniques to improve inventory management, demand forecasting, and route optimization in logistics. However, the challenges of scalability and adaptability remain, mainly in dealing with complicated and dynamic e-commerce warehousing operations. This research proposes the Fractal Deep Learning Model with the Particle Swarm Optimization algorithm (FDLM-PSO) to upgrade the efficacy and adaptability in e-commerce warehousing and logistics. In the FDLM, fractal neural networks support hierarchical learning and processing of multidimensional data related to inventory levels, real-time delivery schedules, and geographic constraints. PSO is a strong optimization technique for dynamic route planning under variable constraints, like traffic and customer priorities, ensuring efficient delivery schedules. Additionally, reinforcement learning is integrated with adaptive inventory control, enabling the real-time creation of decisions aiming at stockouts or overstocking reduction. Results from the proposed model show a 20% reduction in inventory holding cost, a 25% enhancement in delivery time prediction, and a 20% improvement in route efficiency compared to conventional methods. The paper's ability to scale and adapt to high-demand fluctuations attests to its robustness and applicability. The proposed FDLM-PSO addresses critical gaps in the current methodology, developing a scalable and efficient framework for optimizing e-commerce logistics and warehousing operations.
Citation: Huomei Zhou, Wenyu Ning, Tao Guo. A fractal deep learning model for optimizing e-commerce warehousing and logistics[J]. Journal of Industrial and Management Optimization, 2026, 22(1): 374-404. doi: 10.3934/jimo.2026014
E-commerce warehousing and logistics optimization are crucial in meeting increased consumer demand, reducing costs, and improving operational efficiency. Previous work has applied machine learning and deep learning techniques to improve inventory management, demand forecasting, and route optimization in logistics. However, the challenges of scalability and adaptability remain, mainly in dealing with complicated and dynamic e-commerce warehousing operations. This research proposes the Fractal Deep Learning Model with the Particle Swarm Optimization algorithm (FDLM-PSO) to upgrade the efficacy and adaptability in e-commerce warehousing and logistics. In the FDLM, fractal neural networks support hierarchical learning and processing of multidimensional data related to inventory levels, real-time delivery schedules, and geographic constraints. PSO is a strong optimization technique for dynamic route planning under variable constraints, like traffic and customer priorities, ensuring efficient delivery schedules. Additionally, reinforcement learning is integrated with adaptive inventory control, enabling the real-time creation of decisions aiming at stockouts or overstocking reduction. Results from the proposed model show a 20% reduction in inventory holding cost, a 25% enhancement in delivery time prediction, and a 20% improvement in route efficiency compared to conventional methods. The paper's ability to scale and adapt to high-demand fluctuations attests to its robustness and applicability. The proposed FDLM-PSO addresses critical gaps in the current methodology, developing a scalable and efficient framework for optimizing e-commerce logistics and warehousing operations.
| [1] |
A. M. Abed, Accelerate demand forecasting by hybridizing CatBoost with the dingo optimization algorithm to support supply chain conceptual framework precisely, Front. Sustain. , 5 (2024), 1388771. https://doi.org/10.3389/frsus.2024.1388771 doi: 10.3389/frsus.2024.1388771
|
| [2] |
A. Almusawi, S. Pugazhenthi, Innovative resource distribution through multi-agent supply chain scheduling leveraging honey bee optimization techniques, PatternIQ Min., 1 (2024), 48–62. https://doi.org/10.70023/piqm24305 doi: 10.70023/piqm24305
|
| [3] |
W. Cai, Y. Song, Z. Wei, Multimodal data guided spatial feature fusion and grouping strategy for e‐commerce commodity demand forecasting, Mob. Inf. Syst. , 2021 (2021), 5568208. https://doi.org/10.1155/2021/5568208 doi: 10.1155/2021/5568208
|
| [4] | A. J. Chen Jr., Application of Intelligent Logistics Technology in E-Commerce Warehousing: Solutions for Sustainability and Efficiency Issues, Bachelor thesis, Jamk University of Applied Sciences in Finland, 2024. https://urn.fi/URN: NBN: fi: amk-202404268009 |
| [5] |
Z. Chen, J. Liu, Y. Wang, Big data swarm intelligence optimization algorithm application in the intelligent management of an e-commerce logistics warehouse, J. Cases Inf. Technol. , 26 (2024), 1–19. https://doi.org/10.4018/JCIT.332809 doi: 10.4018/JCIT.332809
|
| [6] | U. S. Chigozie, O. C. David, N. E. Nworie, Leveraging artificial intelligence (AI) for business sustainability: a small and medium scale enterprises dimension, Int. J. Public Admin. Manag. Res. , 11 (2025), 28–38. |
| [7] |
D. L. Cortes-Murcia, W. J. Guerrero, J. R. Montoya-Torres, Supply chain management, game-changing technologies, and physical internet: a systematic meta-review of literature, IEEE Access, 10 (2022), 61721–61743. https://doi.org/10.1109/ACCESS.2022.3181154 doi: 10.1109/ACCESS.2022.3181154
|
| [8] | P. Dhawas, A. Dhore, D. Bhagat, R. D. Pawar, A. Kukade, K. Kalbande, Big data preprocessing, techniques, integration, transformation, normalisation, cleaning, discretization, and binning, Big Data Analytics Techniques for Market Intelligence, IGI Global Scientific Publishing, New York, 2024,159–182. https://doi.org/10.4018/979-8-3693-0413-6.ch006 |
| [9] |
S. Dhote, C. Vichoray, R. Pais, S. Baskar, P. Mohamed Shakeel, Hybrid geometric sampling and AdaBoost based deep learning approach for data imbalance in E-commerce, Electron. Commer. Res. , 20 (2020), 259–274. https://doi.org/10.1007/s10660-019-09383-2 doi: 10.1007/s10660-019-09383-2
|
| [10] |
A. C. Gomes, F. B. de Lima Junior, R. D. Soliani, P. R. de Souza Oliveira, D. A. de Oliveira, R. M. Siqueira, et al., Logistics management in e-commerce: challenges and opportunities, Rev. Gest. Secr. , 14 (2023), 7252–7272. https://doi.org/10.7769/gesec.v14i5.2119 doi: 10.7769/gesec.v14i5.2119
|
| [11] |
Z. Gong, Optimization of cross-border E-commerce (CBEC) supply chain management based on fuzzy logic and auction theory, Sci. Rep. , 14 (2024), 14088. https://doi.org/10.1038/s41598-024-64123-3 doi: 10.1038/s41598-024-64123-3
|
| [12] | Instacart Market Basket Analysis. Available from: https://www.kaggle.com/competitions/instacart-market-basket-analysis. |
| [13] | J. Jokela, Optimizing Inventory Management: Leveraging Cnns and Conventional Grouping Methods: A Strategy for Excess Inventory Reduction and Dynamic Grouping, Master thesis, University of Vaasa in Finland, 2024. https://osuva.uwasa.fi/server/api/core/bitstreams/08a7384b-dff9-4655-8421-331bf3068f48/content |
| [14] | K. Lakshman, M. Varalakshmi Reddy and B. K. Sunitha, Online retailing: the past, the present and the future, Yugato, 76 (2024), 1–16. https://www.researchgate.net/publication/380575407_ONLINE_RETAILING_THE_PAST_THE_PRESENT_AND_THE_FUTURE |
| [15] |
Y. Li, T. Chen, ISCCO: a deep learning feature extraction-based strategy framework for dynamic minimization of supply chain transportation cost losses. PeerJ Comput. Sci. , 10 (2024), e2537. https://doi.org/10.7717/peerj-cs.2537 doi: 10.7717/peerj-cs.2537
|
| [16] |
J. Li, T. Cui, K. Yang, R. Yuan, L. He, M. Li, Demand forecasting of e-commerce enterprises based on horizontal federated learning from the perspective of sustainable development, Sustainability, 13 (2021), 13050. https://doi.org/10.3390/su132313050 doi: 10.3390/su132313050
|
| [17] |
M. Mohamed, Toward smart logistics: hybrization of intelligence techniques of machine learning and multi-criteria decision-making in logistics 5.0, Multicriteria Algorithms Appl. , 1 (2023), 42–57. https://doi.org/10.61356/j.mawa.2023.16261 doi: 10.61356/j.mawa.2023.16261
|
| [18] |
Z. Ouyang, E. K. Leung, C. Shen, G. Q. Huang, Synchronizing order picking and delivery in e-commerce warehouses under community logistics, Transport. Res. E-Log. , 188 (2024), 103631. https://doi.org/10.1016/j.tre.2024.103631 doi: 10.1016/j.tre.2024.103631
|
| [19] |
G. Ping, M. Zhu, Z. Ling, K. Niu, Research on optimizing logistics transportation routes using AI large models, Appl. Sci. Eng. J. Adv. Res. , 3 (2024), 14–27. https://doi.org/10.5281/zenodo.12787012 doi: 10.5281/zenodo.12787012
|
| [20] | A. Reyana, S. Kautish, Machine learning techniques for route optimizations and logistics management description, Computational Intelligence Techniques for Sustainable Supply Chain Management, Academic Press, Cambridge, 2024,197–224. https://doi.org/10.1016/B978-0-443-18464-2.00010-8 |
| [21] | A. Rimélé, P. Grangier, M. Gamache, M. Gendreau, L. M. Rousseau, E-commerce warehousing: learning a storage policy, https://doi.org/10.48550/arXiv.2101.08828 |
| [22] |
J. Shi, Research on optimization of cross‐border e‐commerce logistics distribution network in the context of artificial intelligence, Mob. Inf. Syst. , 2022 (2022), 3022280. https://doi.org/10.1155/2022/3022280 doi: 10.1155/2022/3022280
|
| [23] | G. Turken, Z. Temirbekova, L. Naizabayeva, M. M. Barata, Study on Data Warehousing for E-commerce Logistics, DTESI 2023: Proceedings of the 8th International Conference on Digital Technologies in Education, Science and Industry, Almaty, Kazakhstan, 2023. https://api.semanticscholar.org/CorpusID: 269791998 |
| [24] |
Y. Wang, N. M. Coe, Platform ecosystems and digital innovation in food retailing: Exploring the rise of Hema in China, Geoforum, 126 (2021), 310–321. https://doi.org/10.1016/j.geoforum.2021.08.007 doi: 10.1016/j.geoforum.2021.08.007
|
| [25] |
L. Wang, Z. Liu, A. Liu, F. Tao, Artificial intelligence in product lifecycle management, Int. J. Adv. Manuf. Tech. , 114 (2021), 771–796. https://doi.org/10.1007/s00170-021-06882-1 doi: 10.1007/s00170-021-06882-1
|
| [26] | M. Younes, Mapping Logistics Warehouses and Assessing their Socioeconomic Impacts in France with a Focus on E-commerce Activities, Master thesis, University of Lille Prepared at Laboratoire Ville Mobilite Transport in Lille, 2024. https://hal.science/tel-05046048v1 |
| [27] | Y. Zhou, S. Aryal, M. R. Bouadjenek, Review for handling missing data with special missing mechanism, arXiv preprint arXiv: 2404.04905, 2024. https://doi.org/10.48550/arXiv.2404.04905 |
| [28] |
H. Zou, Simulation and optimization system of automated e-commerce logistics warehouse allocation network based on intelligent algorithm, Procedia Comput. Sci. , 243 (2024), 100–107. https://doi.org/10.1016/j.procs.2024.09.014 doi: 10.1016/j.procs.2024.09.014
|
Figures(10) / Tables(10)
Huomei Zhou, Wenyu Ning, Tao Guo. A fractal deep learning model for optimizing e-commerce warehousing and logistics[J]. Journal of Industrial and Management Optimization, 2026, 22(1): 374-404. doi: 10.3934/jimo.2026014
DownLoad: