This paper investigates a machine learning-based logistics network optimization algorithm, aiming to reduce logistics costs, improve transportation efficiency, and enhance service quality by rationally planning transportation routes, optimizing vehicle scheduling, and managing inventory. Traditional logistics network optimization methods, due to their high computational complexity and lack of dynamic adaptability, are unable to meet the demands of modern logistics. Therefore, this paper proposes a machine learning-based logistics network optimization model that can automatically adjust optimization strategies based on real-time data, thereby improving the efficiency and benefits of the logistics network. Experimental results show that the model has achieved significant optimization effects in terms of total cost, service time, vehicle utilization, and inventory turnover rate, and has high practical value and significance for promotion.

Lin Shengtao. Machine Learning-Based Logistics Network Optimization Algorithm. Academic Journal of Computing & Information Science (2025), Vol. 8, Issue 5: 46-54. https://doi.org/10.25236/AJCIS.2025.080505.

[1] Ghosh, S., & Gagné, C. (2020). Machine Learning for Vehicle Routing Problems: A Survey. European Journal of Operational Research, 283(3), 804-821.

[2] Khalil, E. B., Dilkina, B., Song, L., & Wei, D. (2017). Learning Combinatorial Optimization Algorithms over Graphs. Advances in Neural Information Processing Systems, 30.

[3] Lombardi, M., & Milano, M. (2018). Machine Learning for Solving Combinatorial Optimization Problems. AI Magazine, 39(1), 44-55.