Research on optimization of e-commerce supply chain logistics service model based on multi-source data fusion

Inefficiencies in supply chain logistics management, particularly in certain regions, often result in “broken chain” incidents that significantly impact the efficiency of e-commerce operations and degrade consumer experiences. This paper addresses the necessity of optimizing the logistics service model by integrating 12 heterogeneous data sources related to warehousing, transportation, processing, and sorting. We propose a site selection-inventory-path e-commerce logistics optimization model. For the first time, the model incorporates the Dempster-Shafer (D-S) evidence algorithm to quantitatively evaluate the support relationships among various pieces of evidence by adjusting the weight coefficients accordingly. This adjustment is further refined through the application of the Nash equilibrium in the evidence combination process. The optimized logistics model is then solved using a fusion of the model and an intuitive fuzzy set approach. A case study demonstrates that the optimized logistic supply capacity consistently outperformed the non-optimized scenarios, with statistical increases of 1.64%, 1.72%, 2.15%, 3.73%, 2.71%, 2.46%, 3.59%, 2.17%, and 3.98%. Furthermore, by refining the logistics model, the gap in logistics performance was narrowed by at least 5.13% and by as much as 12.9% across successive evaluations, significantly alleviating issues related to enterprise capacity constraints. This study offers novel insights and methodologies for enhancing the efficiency of regional e-commerce supply chain logistics, boosting the competitiveness of logistics enterprises, and elevating the consumer experience in e-commerce settings.