基于STLGBM的供应链韧性空间分异机制研究
A Study on the Spatial Differentiation Mechanism of Supply Chain Resilience Based on STLGBM
DOI: 10.12677/sa.2026.151010, PDF,   
作者: 闫梦铁:河北工业大学理学院,天津
关键词: 供应链韧性STLGBM空间异质性Supply Chain Resilience STLGBM Spatial Heterogeneity
摘要: 本文以2001~2023年中国A股上市公司为研究样本,基于供应链的“链式”特征,采用熵权法对供应链韧性进行定量测度。进一步设计STLGBM模型,通过留局部交叉验证策略优化模型超参数选择,揭示供应链韧性在空间维度上的异质性特征,使用局部重要性得分可视化空间分析中非平稳性的动态变化。研究发现:模型比较表明STLGBM模型拟合程度较好。不同驱动因素共同塑造了供应链韧性的空间异质性格局:东部地区受资产负债率和市场竞争主导,中部以财务杠杆为核心驱动,南部及东南沿海则主要由企业创新能力驱动。
Abstract: This study uses Chinese A-share listed companies from 2001 to 2023 as the research sample. Based on the “chain-like” characteristics of supply chains, the entropy weight method is employed to quantitatively measure supply chain resilience. A STLGBM model is further designed, and a leave-local cross-validation strategy is adopted to optimize hyperparameter selection, revealing the heterogeneous characteristics of supply chain resilience in the spatial dimension. Local importance scores are used to visualize the dynamic changes of non-stationarity in spatial analysis. The research findings indicate that model comparisons demonstrate the STLGBM model exhibits a good fit. Different driving factors collectively shape the spatially heterogeneous pattern of supply chain resilience: the eastern region is dominated by the asset-liability ratio and market competition, the central region is primarily driven by financial leverage, while the southern and southeastern coastal regions are mainly driven by corporate innovation capability.
文章引用:闫梦铁. 基于STLGBM的供应链韧性空间分异机制研究[J]. 统计学与应用, 2026, 15(1): 99-106. https://doi.org/10.12677/sa.2026.151010

参考文献

[1] 白新华, 李国英. 以数实融合提升产业链供应链韧性的现实思考[J]. 区域经济评论, 2023(6): 63-68.
[2] Grossman, G.M., Helpman, E. and Lhuillier, H. (2023) Supply Chain Resilience: Should Policy Promote International Diversification or Reshoring? Journal of Political Economy, 131, 3462-3496. [Google Scholar] [CrossRef
[3] 陶锋, 王欣然, 徐扬, 等. 数字化转型、产业链供应链韧性与企业生产率[J]. 中国工业经济, 2023(5): 118-136.
[4] Bonadio, B., Huo, Z., Levchenko, A.A. and Pandalai-Nayar, N. (2021) Global Supply Chains in the Pandemic. Journal of International Economics, 133, Article ID: 103534. [Google Scholar] [CrossRef] [PubMed]
[5] Luo, Y. and Su, S. (2025) Spatiotemporal Random Forest and Spatiotemporal Stacking Tree: A Novel Spatially Explicit Ensemble Learning Approach to Modeling Non-Linearity in Spatiotemporal Non-Stationarity. International Journal of Applied Earth Observation and Geoinformation, 136, Article ID: 104315. [Google Scholar] [CrossRef
[6] 于蔚, 汪淼军, 金祥荣. 政治关联和融资约束: 信息效应与资源效应[J]. 经济研究, 2012, 47(9): 125-139.