Spatiotemporal Graph Convolution-based Demand Forecasting and Simulation Analysis for Automotive Parts Supply Chain

Authors

Xiaobin Li, College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044, China; State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University, Chongqing 400044, China
Bing Hu, College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044, China; State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University, Chongqing 400044, China
Chao Yin, College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044, China; State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University, Chongqing 400044, China
Bo Li, College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044, China; State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University, Chongqing 400044, China
Jun Ma, Chongqing Tiema Industries Group Co., Ltd., Chongqing 400020, China

Abstract

Abstract: To address complex automotive after-sales parts supply network operations with insufficient demand forecasting accuracy, slow response, and low service efficiency, this study proposed a spatiotemporal graph convolution-based method for automotive parts supply chain demand forecasting. Sales network data of the automotive parts sales network was constructed as a heterogeneous graph, integrating node features like parts sales volume and value to build multi-dimensional node dependencies. A node update mechanism of the graph convolutional neural network was designed, combined with long short-term memory neural networks to capture temporal features, using spatiotemporal attention to integrate temporal and spatial features into updated nodes. Simulation experiments show the method achieves an optimal RMSE of 2.09, error peaks within 3.44 under dynamic disturbances, and recovery within 50 steps, validating its forecasting performance and dynamic adaptability in complex supply chain environments.

Recommended Citation

Li, Xiaobin; Hu, Bing; Yin, Chao; Li, Bo; and Ma, Jun (2025) "Spatiotemporal Graph Convolution-based Demand Forecasting and Simulation Analysis for Automotive Parts Supply Chain," Journal of System Simulation: Vol. 37: Iss. 12, Article 8.
DOI: 10.16182/j.issn1004731x.joss.25-0659
Available at: https://dc-china-simulation.researchcommons.org/journal/vol37/iss12/8

First Page

3060

Last Page

3074

CLC

TP391.9

Recommended Citation

Li Xiaobin, Hu Bing, Yin Chao, et al. Spatiotemporal Graph Convolution-based Demand Forecasting and Simulation Analysis for Automotive Parts Supply Chain[J]. Journal of System Simulation, 2025, 37(12): 3060-3074.

Corresponding Author

Yin Chao

DOI

10.16182/j.issn1004731x.joss.25-0659