With the rapid growth of e-commerce, distribution centers are facing serious challenges caused by a sharp increase in SKU variety and highly fragmented orders. Picking operations have become the main bottleneck restricting warehouse efficiency. This research intends to solve the problem where traditional experience-based layout lags behind dynamic business needs by using a data-driven way. Recency weighted dynamic EIQ evaluation model. Through the introduction of a time decay function, the model can capture recent changes in the popularity of SKUs and achieve more timely ABC classification. Then, to examine the relationship among items, we use SVD to lower the size of the high-dimensional co-picking matrix. Hierarchical clustering is then used to find SKU association clusters. Finally, a cluster-aware storage allocation algorithm is created to allocate high-value clusters to the best physical places. Simulation experiments based on actual orders from a logistics center in eastern China indicate that the proposed method cuts the average walking distance during picking by 19.34 percent. This greatly speeds up order fulfillment and reduces labor costs.

Miao Wang, Jianchun Hao, Hongbo Li, Haoran Liu. Intelligent Warehouse Layout Optimization Based on Dynamic Demand Perception and Co-Picking Behavior Clustering. Academic Journal of Computing & Information Science (2026), Vol. 9, Issue 3: 91-97. https://doi.org/10.25236/AJCIS.2026.090311.

[1] D. Gao, N. Wang, and B. Jiang, “Analysis of Information-Sharing Mechanisms in Online Closed-Loop Supply Chain Systems,” Systems, vol. 13, no. Compendex, 2025, doi: 10.3390/systems13090810.

[2] J. Nuerk and F. Daena, “Systems Engineering Methodology for Digital Supply Chain Business Models,” Systems Engineering, vol. 28, no. Compendex, pp. 411–437, 2025, doi: 10.1002/sys.21802.

[3] X. Chen, F. Li, B. Jia, J. Wu, Z. Gao, and R. Liu, “Optimizing storage location assignment in an automotive Ro-Ro terminal,” Transportation Research Part B: Methodological, vol. 143, no. Compendex, pp. 249–281, 2021, doi: 10.1016/j.trb.2020.10.009.

[4] J. Zhao, K. Liang, F. Wang, H. Liu, J. Yang, and L. Zhou, “Warehouse layout optimization for fishbone robotic mobile fulfillment systems,” Expert Systems with Applications, vol. 259, no. Compendex, 2025, doi: 10.1016/j.eswa.2024.125166.

[5] M. Hosseini, S. Chalil Madathil, and M. T. Khasawneh, “Reinforcement learning-based simulation optimization for an integrated manufacturing-warehouse system: a two-stage approach,” Expert Systems with Applications, vol. 290, no. Compendex, 2025, doi: 10.1016/j.eswa.2025.128259.

[6] Y. Zhu and Y. Zhang, “A game-theoretic cooperative path planning strategy using hybrid heuristic optimization algorithm,” IET Control Theory and Applications, vol. 19, no. Compendex, 2025, doi: 10.1049/cth2.12766.

[7] M. S. Rahman, A. Duary, A. A. Shaikh, and A. K. Bhunia, “An application of real coded Self-organizing Migrating Genetic Algorithm on a two-warehouse inventory problem with Type-2 interval valued inventory costs via mean bounds optimization technique,” Applied Soft Computing, vol. 124, no. Compendex, 2022, doi: 10.1016/j.asoc.2022.109085.

[8] E. Esmaeeli, A. Haji, J. Rezaeenour, M. Sabaghieh Yazd, and M. R. Feylizadeh, “Optimizing truck scheduling and dock placement at cross-docking systems through a hybrid genetic-ant colony optimization algorithm,” Journal of Industrial and Production Engineering, vol. 42, no. Compendex, pp. 938–966, 2025, doi: 10.1080/21681015.2025.2498662.

[9] Z. Luan, L. Yu, Q. Tian, and M. Liu, “Multi-Objective Optimization of Multi-Warehouse Cargo Allocation and Transportation Planning Using an Enhanced Ant Colony Algorithm,” Informatica (Slovenia), vol. 49, no. Compendex, 2025, doi: 10.31449/inf.v49i29.8439.

[10] V. Agarwal, R. K. Gupta, and A. Tiwari, “Multi-Phase Recommender Framework for Pattern Warehousing Using Evolutionary Optimization,” IEEE Access, vol. 13, no. Compendex, pp. 181925–181943, 2025, doi: 10.1109/ACCESS.2025.3622481.